Lea Schönherr

Hossein Hajipour, Keno Hassler, Thorsten Holz et al.

Large language models (LLMs) for automatic code generation have achieved breakthroughs in several programming tasks. Their advances in competition-level programming problems have made them an essential pillar of AI-assisted pair programming, and tools such as GitHub Copilot have emerged as part of the daily programming workflow used by millions of developers. The training data for these models is usually collected from the Internet (e.g., from open-source repositories) and is likely to contain faults and security vulnerabilities. This unsanitized training data can cause the language models to learn these vulnerabilities and propagate them during the code generation procedure. While these models have been extensively assessed for their ability to produce functionally correct programs, there remains a lack of comprehensive investigations and benchmarks addressing the security aspects of these models. In this work, we propose a method to systematically study the security issues of code language models to assess their susceptibility to generating vulnerable code. To this end, we introduce the first approach to automatically find generated code that contains vulnerabilities in black-box code generation models. To achieve this, we present an approach to approximate inversion of the black-box code generation models based on few-shot prompting. We evaluate the effectiveness of our approach by examining code language models in generating high-risk security weaknesses. Furthermore, we establish a collection of diverse non-secure prompts for various vulnerability scenarios using our method. This dataset forms a benchmark for evaluating and comparing the security weaknesses in code language models.

Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad et al.

There is an growing interest in using Large Language Models (LLMs) in multi-agent systems to tackle interactive real-world tasks that require effective collaboration and assessing complex situations. Yet, we still have a limited understanding of LLMs' communication and decision-making abilities in multi-agent setups. The fundamental task of negotiation spans many key features of communication, such as cooperation, competition, and manipulation potentials. Thus, we propose using scorable negotiation to evaluate LLMs. We create a testbed of complex multi-agent, multi-issue, and semantically rich negotiation games. To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities while integrating them in a dynamic and multi-turn setup. We propose multiple metrics to rigorously quantify agents' performance and alignment with the assigned role. We provide procedures to create new games and increase games' difficulty to have an evolving benchmark. Importantly, we evaluate critical safety aspects such as the interaction dynamics between agents influenced by greedy and adversarial players. Our benchmark is highly challenging; GPT-3.5 and small models mostly fail, and GPT-4 and SoTA large models (e.g., Llama-3 70b) still underperform.

Gianluca De Stefano, Lea Schönherr, Giancarlo Pellegrino

Retrieval Augmented Generation (RAG) is a technique commonly used to equip models with out of distribution knowledge. This process involves collecting, indexing, retrieving, and providing information to an LLM for generating responses. Despite its growing popularity due to its flexibility and low cost, the security implications of RAG have not been extensively studied. The data for such systems are often collected from public sources, providing an attacker a gateway for indirect prompt injections to manipulate the responses of the model. In this paper, we investigate the security of RAG systems against end-to-end indirect prompt manipulations. First, we review existing RAG framework pipelines, deriving a prototypical architecture and identifying critical parameters. We then examine prior works searching for techniques that attackers can use to perform indirect prompt manipulations. Finally, we implemented Rag 'n Roll, a framework to determine the effectiveness of attacks against end-to-end RAG applications. Our results show that existing attacks are mostly optimized to boost the ranking of malicious documents during the retrieval phase. However, a higher rank does not immediately translate into a reliable attack. Most attacks, against various configurations, settle around a 40% success rate, which could rise to 60% when considering ambiguous answers as successful attacks (those that include the expected benign one as well). Additionally, when using unoptimized documents, attackers deploying two of them (or more) for a target query can achieve similar results as those using optimized ones. Finally, exploration of the configuration space of a RAG showed limited impact in thwarting the attacks, where the most successful combination severely undermines functionality.

Hossein Hajipour, Lea Schönherr, Thorsten Holz et al.

Large language models (LLMs) have shown great potential for automatic code generation and form the basis for various tools such as GitHub Copilot. However, recent studies highlight that many LLM-generated code contains serious security vulnerabilities. While previous work tries to address this by training models that generate secure code, these attempts remain constrained by limited access to training data and labor-intensive data preparation. In this paper, we introduce HexaCoder, a novel approach to enhance the ability of LLMs to generate secure codes by automatically synthesizing secure codes, which reduces the effort of finding suitable training data. HexaCoder comprises two key components: an oracle-guided data synthesis pipeline and a two-step process for secure code generation. The data synthesis pipeline generates pairs of vulnerable and fixed codes for specific Common Weakness Enumeration (CWE) types by utilizing a state-of-the-art LLM for repairing vulnerable code. A security oracle identifies vulnerabilities, and a state-of-the-art LLM repairs them by extending and/or editing the codes, creating data pairs for fine-tuning using the Low-Rank Adaptation (LoRA) method. Each example of our fine-tuning dataset includes the necessary security-related libraries and code that form the basis of our novel two-step generation approach. This allows the model to integrate security-relevant libraries before generating the main code, significantly reducing the number of generated vulnerable codes by up to 85% compared to the baseline methods. We perform extensive evaluations on three different benchmarks for four LLMs, demonstrating that HexaCoder not only improves the security of the generated code but also maintains a high level of functional correctness.

David Pape, Sina Mavali, Thorsten Eisenhofer et al.

System prompts that include detailed instructions to describe the task performed by the underlying LLM can easily transform foundation models into tools and services with minimal overhead. They are often considered intellectual property, similar to the code of a software product, because of their crucial impact on the utility. However, extracting system prompts is easily possible. As of today, there is no effective countermeasure to prevent the stealing of system prompts, and all safeguarding efforts could be evaded. In this work, we propose an alternative to conventional system prompts. We introduce prompt obfuscation to prevent the extraction of the system prompt with little overhead. The core idea is to find a representation of the original system prompt that leads to the same functionality, while the obfuscated system prompt does not contain any information that allows conclusions to be drawn about the original system prompt. We evaluate our approach by comparing our obfuscated prompt output with the output of the original prompt, using eight distinct metrics to measure the lexical, character-level, and semantic similarity. We show that the obfuscated version is constantly on par with the original one. We further perform three different deobfuscation attacks with varying attacker knowledge--covering both black-box and white-box conditions--and show that in realistic attack scenarios an attacker is unable to extract meaningful information. Overall, we demonstrate that prompt obfuscation is an effective mechanism to safeguard the intellectual property of a system prompt while maintaining the same utility as the original prompt.

David Pape, Jonathan Evertz, Lea Schönherr

Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a percentage point. At the same time, the computational cost of evaluating modern LLMs has driven widespread adoption of specialized inference backends, software systems that execute trained models efficiently at inference time. While critical for scalability, system-level optimizations, such as custom CUDA kernels and reduced-precision arithmetic, can alter token probabilities and introduce non-determinism, possibly cascading into divergent generation. In this work, we first survey the inference landscape, identifying 200 distinct engines, and analyze 35,000 ML publications, finding that the specific inference stack is rarely reported despite this widespread diversity. We then present a systematic empirical study of how inference backends affect LLM benchmark results. Holding model weights, decoding parameters, and hardware constant, we evaluate five widely used inference engines, including vLLM, SGLang, and llama.cpp, across multiple open-weight models and established benchmarks. We show that the choice of backend alone can shift benchmark scores by up to 16.6 percentage points and induce high rates of output disagreement. By isolating backend optimizations and tracing the execution pipeline, we find this divergence is driven by system-level optimizations like prefix caching and CUDA graphs, custom kernels, and engine-specific defaults in logit processing. Our findings identify the inference backend as a previously unreported but consequential hyperparameter in the evaluation of LLM and advocate standardized reporting of inference stacks to improve the reproducibility and interpretability of benchmark comparisons.

Sina Mavali, David Pape, Jonathan Evertz et al.

Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing benchmarks do not capture this ability. An agent may appear capable by blindly following all instructions, or appear robust by ignoring them altogether. We introduce TAB (Task Alignment Benchmark), a suite of 89 terminal tasks derived from Terminal-Bench 2.1. Each task is intentionally underspecified, with missing information provided as a necessary cue embedded in a natural environmental artifact, alongside a plausible but irrelevant distractor. Solving these tasks requires selectively using the cue while ignoring the distractor. Applying TAB to ten frontier agents reveals a systematic gap between task capability and task alignment. The strongest Terminal-Bench agent achieves high task completion but low task alignment on TAB. Evaluating six prompt-injection defenses further shows that suppressing distractor execution also suppresses the cues required for task completion. These results demonstrate that task-aligned agents require selective use of environmental instructions rather than blanket acceptance or rejection.

Edoardo Debenedetti, Javier Rando, Daniel Paleka et al.

Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in the LLM system prompt. The competition was organized in two phases. In the first phase, teams developed defenses to prevent the model from leaking the secret. During the second phase, teams were challenged to extract the secrets hidden for defenses proposed by the other teams. This report summarizes the main insights from the competition. Notably, we found that all defenses were bypassed at least once, highlighting the difficulty of designing a successful defense and the necessity for additional research to protect LLM systems. To foster future research in this direction, we compiled a dataset with over 137k multi-turn attack chats and open-sourced the platform.

Devansh Srivastav, David Pape, Lea Schönherr

LLMs are increasingly embedded in everyday decision-making, yet their outputs can encode subtle, unintended behaviours that shape user beliefs and actions. We refer to these covert, goal-directed behaviours as hidden intentions, which may arise from training and optimisation artefacts, or be deliberately induced by an adversarial developer, yet remain difficult to detect in practice. We introduce a taxonomy of ten categories of hidden intentions, grounded in social science research and organised by intent, mechanism, context, and impact, shifting attention from surface-level behaviours to design-level strategies of influence. We show how hidden intentions can be easily induced in controlled models, providing both testbeds for evaluation and demonstrations of potential misuse. We systematically assess detection methods, including reasoning and non-reasoning LLM judges, and find that detection collapses in realistic open-world settings, particularly under low-prevalence conditions, where false positives overwhelm precision and false negatives conceal true risks. Stress tests on precision-prevalence and precision-FNR trade-offs reveal why auditing fails without vanishingly small false positive rates or strong priors on manipulation types. Finally, a qualitative case study shows that all ten categories manifest in deployed, state-of-the-art LLMs, emphasising the urgent need for robust frameworks. Our work provides the first systematic analysis of detectability failures of hidden intentions in LLMs under open-world settings, offering a foundation for understanding, inducing, and stress-testing such behaviours, and establishing a flexible taxonomy for anticipating evolving threats and informing governance.

Antonio Emanuele Cinà, Francesco Villani, Maura Pintor et al.

Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider $\ell_2$- and $\ell_\infty$-norm constraints to craft input perturbations, only a few investigate sparse $\ell_1$- and $\ell_0$-norm attacks. In particular, $\ell_0$-norm attacks remain the least studied due to the inherent complexity of optimizing over a non-convex and non-differentiable constraint. However, evaluating adversarial robustness under these attacks could reveal weaknesses otherwise left untested with more conventional $\ell_2$- and $\ell_\infty$-norm attacks. In this work, we propose a novel $\ell_0$-norm attack, called $σ$-zero, which leverages a differentiable approximation of the $\ell_0$ norm to facilitate gradient-based optimization, and an adaptive projection operator to dynamically adjust the trade-off between loss minimization and perturbation sparsity. Extensive evaluations using MNIST, CIFAR10, and ImageNet datasets, involving robust and non-robust models, show that $σ$\texttt{-zero} finds minimum $\ell_0$-norm adversarial examples without requiring any time-consuming hyperparameter tuning, and that it outperforms all competing sparse attacks in terms of success rate, perturbation size, and efficiency.

Sandra Höltervennhoff, Jonas Ricker, Maike M. Raphael et al.

Generative artificial intelligence is developing rapidly, impacting humans' interaction with information and digital media. It is increasingly used to create deceptively realistic misinformation, so lawmakers have imposed regulations requiring the disclosure of AI-generated content. However, only little is known about whether these labels reduce the risks of AI-generated misinformation. Our work addresses this research gap. Focusing on AI-generated images, we study the implications of labels, including the possibility of mislabeling. Assuming that simplicity, transparency, and trust are likely to impact the successful adoption of such labels, we first qualitatively explore users' opinions and expectations of AI labeling using five focus groups. Second, we conduct a pre-registered online survey with over 1300 U.S. and EU participants to quantitatively assess the effect of AI labels on users' ability to recognize misinformation containing either human-made or AI-generated images. Our focus groups illustrate that, while participants have concerns about the practical implementation of labeling, they consider it helpful in identifying AI-generated images and avoiding deception. However, considering security benefits, our survey revealed an ambiguous picture, suggesting that users might over-rely on labels. While inaccurate claims supported by labeled AI-generated images were rated less credible than those with unlabeled AI-images, the belief in accurate claims also decreased when accompanied by a labeled AI-generated image. Moreover, we find the undesired side effect that human-made images conveying inaccurate claims were perceived as more credible in the presence of labels.

Rostislav Makarov, Lea Schönherr, Timo Gerkmann

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced speech enhancement models can be susceptible to adversarial attacks. Specifically, we show that adversarial noise, carefully crafted and psychoacoustically masked by the original input, can be injected such that the enhanced speech output conveys an entirely different semantic meaning. We experimentally verify that contemporary predictive speech enhancement models can indeed be manipulated in this way. Furthermore, we highlight that diffusion models with stochastic samplers exhibit inherent robustness to such adversarial attacks by design.

Srishti Gupta, Daniele Angioni, Maura Pintor et al.

Class-incremental learning (CIL) poses significant challenges in open-world scenarios, where models must not only learn new classes over time without forgetting previous ones but also handle inputs from unknown classes that a closed-set model would misclassify. Recent works address both issues by (i)~training multi-head models using the task-incremental learning framework, and (ii) predicting the task identity employing out-of-distribution (OOD) detectors. While effective, the latter mainly relies on joint training with a memory buffer of past data, raising concerns around privacy, scalability, and increased training time. In this paper, we present an in-depth analysis of post-hoc OOD detection methods and investigate their potential to eliminate the need for a memory buffer. We uncover that these methods, when applied appropriately at inference time, can serve as a strong substitute for buffer-based OOD detection. We show that this buffer-free approach achieves comparable or superior performance to buffer-based methods both in terms of class-incremental learning and the rejection of unknown samples. Experimental results on CIFAR-10, CIFAR-100 and Tiny ImageNet datasets support our findings, offering new insights into the design of efficient and privacy-preserving CIL systems for open-world settings.

João Borges S. Carvalho, Victor Jimenez Rodriguez, Alessandro Torcinovich et al.

The robustness of algorithms against covariate shifts is a fundamental problem with critical implications for the deployment of machine learning algorithms in the real world. Current evaluation methods predominantly measure robustness through the lens of standard generalization, relying on task performance measures like accuracy. This approach lacks a theoretical justification and underscores the need for a principled foundation of robustness assessment under distribution shifts. In this work, we set the desiderata for a robustness measure, and we propose a novel principled framework for the robustness assessment problem that directly follows the Posterior Agreement (PA) theory of model validation. Specifically, we extend the PA framework to the covariate shift setting and propose a measure for robustness evaluation. We assess the soundness of our measure in controlled environments and through an empirical robustness analysis in two different covariate shift scenarios: adversarial learning and domain generalization. We illustrate the suitability of PA by evaluating several models under different nature and magnitudes of shift, and proportion of affected observations. The results show that PA offers a reliable analysis of the vulnerabilities in learning algorithms across different shift conditions and provides higher discriminability than accuracy-based measures, while requiring no supervision.

Jonathan Evertz, Merlin Chlosta, Lea Schönherr et al.

The interaction between users and applications is increasingly shifted toward natural language by deploying Large Language Models (LLMs) as the core interface. The capabilities of these so-called agents become more capable the more tools and services they serve as an interface for, ultimately leading to agentic systems. Agentic systems use LLM-based agents as interfaces for most user interactions and various integrations with external tools and services. While these interfaces can significantly enhance the capabilities of the agentic system, they also introduce a new attack surface. Manipulated integrations, for example, can exploit the internal LLM and compromise sensitive data accessed through other interfaces. While previous work primarily focused on attacks targeting a model's alignment or the leakage of training data, the security of data that is only available during inference has escaped scrutiny so far. In this work, we demonstrate how the integration of LLMs into systems with external tool integration poses a risk similar to established prompt-based attacks, able to compromise the confidentiality of the entire system. Introducing a systematic approach to evaluate these confidentiality risks, we identify two specific attack scenarios unique to these agentic systems and formalize these into a tool-robustness framework designed to measure a model's ability to protect sensitive information. Our analysis reveals significant vulnerabilities across all tested models, highlighting an increased risk when models are combined with external tools.

Joel Frank, Franziska Herbert, Jonas Ricker et al.

AI-generated media has become a threat to our digital society as we know it. These forgeries can be created automatically and on a large scale based on publicly available technology. Recognizing this challenge, academics and practitioners have proposed a multitude of automatic detection strategies to detect such artificial media. However, in contrast to these technical advances, the human perception of generated media has not been thoroughly studied yet. In this paper, we aim at closing this research gap. We perform the first comprehensive survey into people's ability to detect generated media, spanning three countries (USA, Germany, and China) with 3,002 participants across audio, image, and text media. Our results indicate that state-of-the-art forgeries are almost indistinguishable from "real" media, with the majority of participants simply guessing when asked to rate them as human- or machine-generated. In addition, AI-generated media receive is voted more human like across all media types and all countries. To further understand which factors influence people's ability to detect generated media, we include personal variables, chosen based on a literature review in the domains of deepfake and fake news research. In a regression analysis, we found that generalized trust, cognitive reflection, and self-reported familiarity with deepfakes significantly influence participant's decision across all media categories.

David Pape, Sina Däubener, Thorsten Eisenhofer et al.

Model stealing aims at inferring a victim model's functionality at a fraction of the original training cost. While the goal is clear, in practice the model's architecture, weight dimension, and original training data can not be determined exactly, leading to mutual uncertainty during stealing. In this work, we explicitly tackle this uncertainty by generating multiple possible networks and combining their predictions to improve the quality of the stolen model. For this, we compare five popular uncertainty quantification models in a model stealing task. Surprisingly, our results indicate that the considered models only lead to marginal improvements in terms of label agreement (i.e., fidelity) to the stolen model. To find the cause of this, we inspect the diversity of the model's prediction by looking at the prediction variance as a function of training iterations. We realize that during training, the models tend to have similar predictions, indicating that the network diversity we wanted to leverage using uncertainty quantification models is not (high) enough for improvements on the model stealing task.

Joel Frank, Lea Schönherr

Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes" has emerged. This research most often focuses on the image domain, while studies exploring generated audio signals have, so-far, been neglected. In this paper we make three key contributions to narrow this gap. First, we provide researchers with an introduction to common signal processing techniques used for analyzing audio signals. Second, we present a novel data set, for which we collected nine sample sets from five different network architectures, spanning two languages. Finally, we supply practitioners with two baseline models, adopted from the signal processing community, to facilitate further research in this area.

Thorsten Eisenhofer, Lea Schönherr, Joel Frank et al.

Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmless to human observers. In our digital society, this poses a significant threat. For example, Automatic Speech Recognition (ASR) systems, which serve as hands-free interfaces to many kinds of systems, can be attacked with inputs incomprehensible for human listeners. The research community has unsuccessfully tried several approaches to tackle this problem. In this paper we propose a different perspective: We accept the presence of adversarial examples against ASR systems, but we require them to be perceivable by human listeners. By applying the principles of psychoacoustics, we can remove semantically irrelevant information from the ASR input and train a model that resembles human perception more closely. We implement our idea in a tool named DOMPTEUR and demonstrate that our augmented system, in contrast to an unmodified baseline, successfully focuses on perceptible ranges of the input signal. This change forces adversarial examples into the audible range, while using minimal computational overhead and preserving benign performance. To evaluate our approach, we construct an adaptive attacker that actively tries to avoid our augmentations and demonstrate that adversarial examples from this attacker remain clearly perceivable. Finally, we substantiate our claims by performing a hearing test with crowd-sourced human listeners.

Hojjat Aghakhani, Lea Schönherr, Thorsten Eisenhofer et al.

Despite remarkable improvements, automatic speech recognition is susceptible to adversarial perturbations. Compared to standard machine learning architectures, these attacks are significantly more challenging, especially since the inputs to a speech recognition system are time series that contain both acoustic and linguistic properties of speech. Extracting all recognition-relevant information requires more complex pipelines and an ensemble of specialized components. Consequently, an attacker needs to consider the entire pipeline. In this paper, we present VENOMAVE, the first training-time poisoning attack against speech recognition. Similar to the predominantly studied evasion attacks, we pursue the same goal: leading the system to an incorrect and attacker-chosen transcription of a target audio waveform. In contrast to evasion attacks, however, we assume that the attacker can only manipulate a small part of the training data without altering the target audio waveform at runtime. We evaluate our attack on two datasets: TIDIGITS and Speech Commands. When poisoning less than 0.17% of the dataset, VENOMAVE achieves attack success rates of more than 80.0%, without access to the victim's network architecture or hyperparameters. In a more realistic scenario, when the target audio waveform is played over the air in different rooms, VENOMAVE maintains a success rate of up to 73.3%. Finally, VENOMAVE achieves an attack transferability rate of 36.4% between two different model architectures.

Lea Schönherr, Maximilian Golla, Thorsten Eisenhofer et al.

Voice assistants like Amazon's Alexa, Google's Assistant, or Apple's Siri, have become the primary (voice) interface in smart speakers that can be found in millions of households. For privacy reasons, these speakers analyze every sound in their environment for their respective wake word like ''Alexa'' or ''Hey Siri,'' before uploading the audio stream to the cloud for further processing. Previous work reported on the inaccurate wake word detection, which can be tricked using similar words or sounds like ''cocaine noodles'' instead of ''OK Google.'' In this paper, we perform a comprehensive analysis of such accidental triggers, i.,e., sounds that should not have triggered the voice assistant, but did. More specifically, we automate the process of finding accidental triggers and measure their prevalence across 11 smart speakers from 8 different manufacturers using everyday media such as TV shows, news, and other kinds of audio datasets. To systematically detect accidental triggers, we describe a method to artificially craft such triggers using a pronouncing dictionary and a weighted, phone-based Levenshtein distance. In total, we have found hundreds of accidental triggers. Moreover, we explore potential gender and language biases and analyze the reproducibility. Finally, we discuss the resulting privacy implications of accidental triggers and explore countermeasures to reduce and limit their impact on users' privacy. To foster additional research on these sounds that mislead machine learning models, we publish a dataset of more than 1000 verified triggers as a research artifact.

Sina Däubener, Lea Schönherr, Asja Fischer et al.

Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the input. In the case of ASR systems, the most interesting cases are targeted attacks, in which an attacker aims to force the system into recognizing given target transcriptions in an arbitrary audio sample. The increasing number of sophisticated, quasi imperceptible attacks raises the question of countermeasures. In this paper, we focus on hybrid ASR systems and compare four acoustic models regarding their ability to indicate uncertainty under attack: a feed-forward neural network and three neural networks specifically designed for uncertainty quantification, namely a Bayesian neural network, Monte Carlo dropout, and a deep ensemble. We employ uncertainty measures of the acoustic model to construct a simple one-class classification model for assessing whether inputs are benign or adversarial. Based on this approach, we are able to detect adversarial examples with an area under the receiving operator curve score of more than 0.99. The neural networks for uncertainty quantification simultaneously diminish the vulnerability to the attack, which is reflected in a lower recognition accuracy of the malicious target text in comparison to a standard hybrid ASR system.

Joel Frank, Thorsten Eisenhofer, Lea Schönherr et al.

Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While deep fake images have been thoroughly investigated in the image domain - a classical approach from the area of image forensics - an analysis in the frequency domain has been missing so far. In this paper, we address this shortcoming and our results reveal that in frequency space, GAN-generated images exhibit severe artifacts that can be easily identified. We perform a comprehensive analysis, showing that these artifacts are consistent across different neural network architectures, data sets, and resolutions. In a further investigation, we demonstrate that these artifacts are caused by upsampling operations found in all current GAN architectures, indicating a structural and fundamental problem in the way images are generated via GANs. Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.

Lea Schönherr, Thorsten Eisenhofer, Steffen Zeiler et al.

Automatic speech recognition (ASR) systems can be fooled via targeted adversarial examples, which induce the ASR to produce arbitrary transcriptions in response to altered audio signals. However, state-of-the-art adversarial examples typically have to be fed into the ASR system directly, and are not successful when played in a room. The few published over-the-air adversarial examples fall into one of three categories: they are either handcrafted examples, they are so conspicuous that human listeners can easily recognize the target transcription once they are alerted to its content, or they require precise information about the room where the attack takes place, and are hence not transferable to other rooms. In this paper, we demonstrate the first algorithm that produces generic adversarial examples, which remain robust in an over-the-air attack that is not adapted to the specific environment. Hence, no prior knowledge of the room characteristics is required. Instead, we use room impulse responses (RIRs) to compute robust adversarial examples for arbitrary room characteristics and employ the ASR system Kaldi to demonstrate the attack. Further, our algorithm can utilize psychoacoustic methods to hide changes of the original audio signal below the human thresholds of hearing. In practical experiments, we show that the adversarial examples work for varying room setups, and that no direct line-of-sight between speaker and microphone is necessary. As a result, an attacker can create inconspicuous adversarial examples for any target transcription and apply these to arbitrary room setups without any prior knowledge.

Lea Schönherr, Katharina Kohls, Steffen Zeiler et al.

Voice interfaces are becoming accepted widely as input methods for a diverse set of devices. This development is driven by rapid improvements in automatic speech recognition (ASR), which now performs on par with human listening in many tasks. These improvements base on an ongoing evolution of DNNs as the computational core of ASR. However, recent research results show that DNNs are vulnerable to adversarial perturbations, which allow attackers to force the transcription into a malicious output. In this paper, we introduce a new type of adversarial examples based on psychoacoustic hiding. Our attack exploits the characteristics of DNN-based ASR systems, where we extend the original analysis procedure by an additional backpropagation step. We use this backpropagation to learn the degrees of freedom for the adversarial perturbation of the input signal, i.e., we apply a psychoacoustic model and manipulate the acoustic signal below the thresholds of human perception. To further minimize the perceptibility of the perturbations, we use forced alignment to find the best fitting temporal alignment between the original audio sample and the malicious target transcription. These extensions allow us to embed an arbitrary audio input with a malicious voice command that is then transcribed by the ASR system, with the audio signal remaining barely distinguishable from the original signal. In an experimental evaluation, we attack the state-of-the-art speech recognition system Kaldi and determine the best performing parameter and analysis setup for different types of input. Our results show that we are successful in up to 98% of cases with a computational effort of fewer than two minutes for a ten-second audio file. Based on user studies, we found that none of our target transcriptions were audible to human listeners, who still understand the original speech content with unchanged accuracy.