Erwin Quiring

Thorsten Eisenhofer, Erwin Quiring, Jonas Möller et al.

The number of papers submitted to academic conferences is steadily rising in many scientific disciplines. To handle this growth, systems for automatic paper-reviewer assignments are increasingly used during the reviewing process. These systems use statistical topic models to characterize the content of submissions and automate the assignment to reviewers. In this paper, we show that this automation can be manipulated using adversarial learning. We propose an attack that adapts a given paper so that it misleads the assignment and selects its own reviewers. Our attack is based on a novel optimization strategy that alternates between the feature space and problem space to realize unobtrusive changes to the paper. To evaluate the feasibility of our attack, we simulate the paper-reviewer assignment of an actual security conference (IEEE S&P) with 165 reviewers on the program committee. Our results show that we can successfully select and remove reviewers without access to the assignment system. Moreover, we demonstrate that the manipulated papers remain plausible and are often indistinguishable from benign submissions.

Vera Wesselkamp, Konrad Rieck, Daniel Arp et al.

Generative adversarial networks (GANs) have made remarkable progress in synthesizing realistic-looking images that effectively outsmart even humans. Although several detection methods can recognize these deep fakes by checking for image artifacts from the generation process, multiple counterattacks have demonstrated their limitations. These attacks, however, still require certain conditions to hold, such as interacting with the detection method or adjusting the GAN directly. In this paper, we introduce a novel class of simple counterattacks that overcomes these limitations. In particular, we show that an adversary can remove indicative artifacts, the GAN fingerprint, directly from the frequency spectrum of a generated image. We explore different realizations of this removal, ranging from filtering high frequencies to more nuanced frequency-peak cleansing. We evaluate the performance of our attack with different detection methods, GAN architectures, and datasets. Our results show that an adversary can often remove GAN fingerprints and thus evade the detection of generated images.

Jonas Ricker, Asja Fischer, Erwin Quiring

Given the surge of harmful AI-generated imagery online, reliably distinguishing authentic images from generated ones has become an urgent research topic. While many proposed detection methods perform well under controlled settings, they often collapse when tested on real-world data. A potential root cause are subtle biases in the detectors' training data. As a result, detectors may rely on spurious correlations instead of learning true forensic artifacts. While a recent line of work has identified the problem, there is not yet an established protocol to evaluate how biased a detector actually is. In this work, we therefore take a step back: First, we discuss what it means for a detector to be biased, and how this differs from a lack of robustness. Second, we propose BIAS-ID, a transparent framework for analyzing and quantifying the presence of transformation biases in AI-generated image detectors. We validate our framework by performing an evaluation of six detectors across two datasets, revealing that several state-of-the-art detection methods are strongly affected by biases. Our results highlight the importance of bias-aware evaluation for developing reliable AI-generated image detectors.

Micha Horlboge, Erwin Quiring, Roland Meyer et al.

The source code of a program not only defines its semantics but also contains subtle clues that can identify its author. Several studies have shown that these clues can be automatically extracted using machine learning and allow for determining a program's author among hundreds of programmers. This attribution poses a significant threat to developers of anti-censorship and privacy-enhancing technologies, as they become identifiable and may be prosecuted. An ideal protection from this threat would be the anonymization of source code. However, neither theoretical nor practical principles of such an anonymization have been explored so far. In this paper, we tackle this problem and develop a framework for reasoning about code anonymization. We prove that the task of generating a $k$-anonymous program -- a program that cannot be attributed to one of $k$ authors -- is not computable in the general case. As a remedy, we introduce a relaxed concept called $k$-uncertainty, which enables us to measure the protection of developers. Based on this concept, we empirically study candidate techniques for anonymization, such as code normalization, coding style imitation, and code obfuscation. We find that none of the techniques provides sufficient protection when the attacker is aware of the anonymization. While we observe a notable reduction in attribution performance on real-world code, a reliable protection is not achieved for all developers. We conclude that code anonymization is a hard problem that requires further attention from the research community.

Erwin Quiring, Andreas Müller, Konrad Rieck

Image scaling is an integral part of machine learning and computer vision systems. Unfortunately, this preprocessing step is vulnerable to so-called image-scaling attacks where an attacker makes unnoticeable changes to an image so that it becomes a new image after scaling. This opens up new ways for attackers to control the prediction or to improve poisoning and backdoor attacks. While effective techniques exist to prevent scaling attacks, their detection has not been rigorously studied yet. Consequently, it is currently not possible to reliably spot these attacks in practice. This paper presents the first in-depth systematization and analysis of detection methods for image-scaling attacks. We identify two general detection paradigms and derive novel methods from them that are simple in design yet significantly outperform previous work. We demonstrate the efficacy of these methods in a comprehensive evaluation with all major learning platforms and scaling algorithms. First, we show that image-scaling attacks modifying the entire scaled image can be reliably detected even under an adaptive adversary. Second, we find that our methods provide strong detection performance even if only minor parts of the image are manipulated. As a result, we can introduce a novel protection layer against image-scaling attacks.

Andreas Müller, Denis Lukovnikov, Jonas Thietke et al.

Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of watermarking techniques that are easy to implement and highly robust against various perturbations. However, our work demonstrates a fundamental security vulnerability of semantic watermarks. We show that attackers can leverage unrelated models, even with different latent spaces and architectures (UNet vs DiT), to perform powerful and realistic forgery attacks. Specifically, we design two watermark forgery attacks. The first imprints a targeted watermark into real images by manipulating the latent representation of an arbitrary image in an unrelated LDM to get closer to the latent representation of a watermarked image. We also show that this technique can be used for watermark removal. The second attack generates new images with the target watermark by inverting a watermarked image and re-generating it with an arbitrary prompt. Both attacks just need a single reference image with the target watermark. Overall, our findings question the applicability of semantic watermarks by revealing that attackers can easily forge or remove these watermarks under realistic conditions.

Jonas Ricker, Dennis Assenmacher, Thorsten Holz et al.

Recent advances in the field of generative artificial intelligence (AI) have blurred the lines between authentic and machine-generated content, making it almost impossible for humans to distinguish between such media. One notable consequence is the use of AI-generated images for fake profiles on social media. While several types of disinformation campaigns and similar incidents have been reported in the past, a systematic analysis has been lacking. In this work, we conduct the first large-scale investigation of the prevalence of AI-generated profile pictures on Twitter. We tackle the challenges of a real-world measurement study by carefully integrating various data sources and designing a multi-stage detection pipeline. Our analysis of nearly 15 million Twitter profile pictures shows that 0.052% were artificially generated, confirming their notable presence on the platform. We comprehensively examine the characteristics of these accounts and their tweet content, and uncover patterns of coordinated inauthentic behavior. The results also reveal several motives, including spamming and political amplification campaigns. Our research reaffirms the need for effective detection and mitigation strategies to cope with the potential negative effects of generative AI in the future.

Andreas Müller, Erwin Quiring

Resource efficiency plays an important role for machine learning nowadays. The energy and decision latency are two critical aspects to ensure a sustainable and practical application. Unfortunately, the energy consumption and decision latency are not robust against adversaries. Researchers have recently demonstrated that attackers can compute and submit so-called sponge examples at inference time to increase the energy consumption and decision latency of neural networks. In computer vision, the proposed strategy crafts inputs with less activation sparsity which could otherwise be used to accelerate the computation. In this paper, we analyze the mechanism how these energy-latency attacks reduce activation sparsity. In particular, we find that input uniformity is a key enabler. A uniform image, that is, an image with mostly flat, uniformly colored surfaces, triggers more activations due to a specific interplay of convolution, batch normalization, and ReLU activation. Based on these insights, we propose two new simple, yet effective strategies for crafting sponge examples: sampling images from a probability distribution and identifying dense, yet inconspicuous inputs in natural datasets. We empirically examine our findings in a comprehensive evaluation with multiple image classification models and show that our attack achieves the same sparsity effect as prior sponge-example methods, but at a fraction of computation effort. We also show that our sponge examples transfer between different neural networks. Finally, we discuss applications of our findings for the good by improving efficiency by increasing sparsity.

Jonas Thietke, Andreas Müller, Denis Lukovnikov et al.

Semantic watermarking methods enable the direct integration of watermarks into the generation process of latent diffusion models by only modifying the initial latent noise. One line of approaches building on Gaussian Shading relies on cryptographic primitives to steer the sampling process of the latent noise. However, we identify several issues in the usage of cryptographic techniques in Gaussian Shading, particularly in its proof of lossless performance and key management, causing ambiguity in follow-up works, too. In this work, we therefore revisit the cryptographic primitives for semantic watermarking. We introduce a novel, general proof of lossless performance based on IND\$-CPA security for semantic watermarks. We then discuss the configuration of the cryptographic primitives in semantic watermarks with respect to security, efficiency, and generation quality.

Denis Lukovnikov, Andreas Müller, Erwin Quiring et al.

In-generation watermarking for detecting and attributing generated content has recently been explored for latent diffusion models (LDMs), demonstrating high robustness. However, the use of in-generation watermarks in autoregressive (AR) image models has not been explored yet. AR models generate images by autoregressively predicting a sequence of visual tokens that are then decoded into pixels using a vector-quantized decoder. Inspired by red-green watermarks for large language models, we examine token-level watermarking schemes that bias the next-token prediction based on prior tokens. We find that a direct transfer of these schemes works in principle, but the detectability of the watermarks decreases considerably under common image perturbations. As a remedy, we propose two novel watermarking methods that rely on visual token clustering to assign similar tokens to the same set. Firstly, we investigate a training-free approach that relies on a cluster lookup table, and secondly, we finetune VAE encoders to predict token clusters directly from perturbed images. Overall, our experiments show that cluster-level watermarks improve robustness against perturbations and regeneration attacks while preserving image quality. Cluster classification further boosts watermark detectability, outperforming a set of baselines. Moreover, our methods offer fast verification runtime, comparable to lightweight post-hoc watermarking methods.

Erwin Quiring, Lukas Pirch, Michael Reimsbach et al.

Machine learning-based systems for malware detection operate in a hostile environment. Consequently, adversaries will also target the learning system and use evasion attacks to bypass the detection of malware. In this paper, we outline our learning-based system PEberus that got the first place in the defender challenge of the Microsoft Evasion Competition, resisting a variety of attacks from independent attackers. Our system combines multiple, diverse defenses: we address the semantic gap, use various classification models, and apply a stateful defense. This competition gives us the unique opportunity to examine evasion attacks under a realistic scenario. It also highlights that existing machine learning methods can be hardened against attacks by thoroughly analyzing the attack surface and implementing concepts from adversarial learning. Our defense can serve as an additional baseline in the future to strengthen the research on secure learning.

Daniel Arp, Erwin Quiring, Feargus Pendlebury et al.

With the growing processing power of computing systems and the increasing availability of massive datasets, machine learning algorithms have led to major breakthroughs in many different areas. This development has influenced computer security, spawning a series of work on learning-based security systems, such as for malware detection, vulnerability discovery, and binary code analysis. Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance and render learning-based systems potentially unsuitable for security tasks and practical deployment. In this paper, we look at this problem with critical eyes. First, we identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We conduct a study of 30 papers from top-tier security conferences within the past 10 years, confirming that these pitfalls are widespread in the current security literature. In an empirical analysis, we further demonstrate how individual pitfalls can lead to unrealistic performance and interpretations, obstructing the understanding of the security problem at hand. As a remedy, we propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible. Furthermore, we identify open problems when applying machine learning in security and provide directions for further research.

Erwin Quiring, Konrad Rieck

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the attacks. In this paper, we propose a novel strategy for hiding backdoor and poisoning attacks. Our approach builds on a recent class of attacks against image scaling. These attacks enable manipulating images such that they change their content when scaled to a specific resolution. By combining poisoning and image-scaling attacks, we can conceal the trigger of backdoors as well as hide the overlays of clean-label poisoning. Furthermore, we consider the detection of image-scaling attacks and derive an adaptive attack. In an empirical evaluation, we demonstrate the effectiveness of our strategy. First, we show that backdoors and poisoning work equally well when combined with image-scaling attacks. Second, we demonstrate that current detection defenses against image-scaling attacks are insufficient to uncover our manipulations. Overall, our work provides a novel means for hiding traces of manipulations, being applicable to different poisoning approaches.

Jacopo Cortellazzi, Feargus Pendlebury, Daniel Arp et al.

Recent research efforts on adversarial machine learning (ML) have investigated problem-space attacks, focusing on the generation of real evasive objects in domains where, unlike images, there is no clear inverse mapping to the feature space (e.g., software). However, the design, comparison, and real-world implications of problem-space attacks remain underexplored. This article makes three major contributions. Firstly, we propose a general formalization for adversarial ML evasion attacks in the problem-space, which includes the definition of a comprehensive set of constraints on available transformations, preserved semantics, absent artifacts, and plausibility. We shed light on the relationship between feature space and problem space, and we introduce the concept of side-effect features as the by-product of the inverse feature-mapping problem. This enables us to define and prove necessary and sufficient conditions for the existence of problem-space attacks. Secondly, building on our general formalization, we propose a novel problem-space attack on Android malware that overcomes past limitations in terms of semantics and artifacts. We have tested our approach on a dataset with 150K Android apps from 2016 and 2018 which show the practical feasibility of evading a state-of-the-art malware classifier along with its hardened version. Thirdly, we explore the effectiveness of adversarial training as a possible approach to enforce robustness against adversarial samples, evaluating its effectiveness on the considered machine learning models under different scenarios. Our results demonstrate that "adversarial-malware as a service" is a realistic threat, as we automatically generate thousands of realistic and inconspicuous adversarial applications at scale, where on average it takes only a few minutes to generate an adversarial instance.

Erwin Quiring, Matthias Kirchner, Konrad Rieck

Camera sensor noise is one of the most reliable device characteristics in digital image forensics, enabling the unique linkage of images to digital cameras. This so-called camera fingerprint gives rise to different applications, such as image forensics and authentication. However, if images are publicly available, an adversary can estimate the fingerprint from her victim and plant it into spurious images. The concept of fragile camera fingerprints addresses this attack by exploiting asymmetries in data access: While the camera owner will always have access to a full fingerprint from uncompressed images, the adversary has typically access to compressed images and thus only to a truncated fingerprint. The security of this defense, however, has not been systematically explored yet. This paper provides the first comprehensive analysis of fragile camera fingerprints under attack. A series of theoretical and practical tests demonstrate that fragile camera fingerprints allow a reliable device identification for common compression levels in an adversarial environment.

Erwin Quiring, Alwin Maier, Konrad Rieck

In this paper, we present a novel attack against authorship attribution of source code. We exploit that recent attribution methods rest on machine learning and thus can be deceived by adversarial examples of source code. Our attack performs a series of semantics-preserving code transformations that mislead learning-based attribution but appear plausible to a developer. The attack is guided by Monte-Carlo tree search that enables us to operate in the discrete domain of source code. In an empirical evaluation with source code from 204 programmers, we demonstrate that our attack has a substantial effect on two recent attribution methods, whose accuracy drops from over 88% to 1% under attack. Furthermore, we show that our attack can imitate the coding style of developers with high accuracy and thereby induce false attributions. We conclude that current approaches for authorship attribution are inappropriate for practical application and there is a need for resilient analysis techniques.

Erwin Quiring, Daniel Arp, Konrad Rieck

Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind and thus are vulnerable to different types of attacks. This problem has motivated the research field of adversarial machine learning that is concerned with attacking and defending learning methods. Concurrently, a different line of research has tackled a very similar problem: In digital watermarking information are embedded in a signal in the presence of an adversary. As a consequence, this research field has also extensively studied techniques for attacking and defending watermarking methods. The two research communities have worked in parallel so far, unnoticeably developing similar attack and defense strategies. This paper is a first effort to bring these communities together. To this end, we present a unified notation of black-box attacks against machine learning and watermarking that reveals the similarity of both settings. To demonstrate the efficacy of this unified view, we apply concepts from watermarking to machine learning and vice versa. We show that countermeasures from watermarking can mitigate recent model-extraction attacks and, similarly, that techniques for hardening machine learning can fend off oracle attacks against watermarks. Our work provides a conceptual link between two research fields and thereby opens novel directions for improving the security of both, machine learning and digital watermarking.