Weifei Jin

Weifei Jin, Yuxin Cao, Junjie Su et al.

Recent advances in Audio-Language Models (ALMs) have significantly improved multimodal understanding capabilities. However, the introduction of the audio modality also brings new and unique vulnerability vectors. Previous studies have proposed jailbreak attacks that specifically target ALMs, revealing that defenses directly transferred from traditional audio adversarial attacks or text-based Large Language Model (LLM) jailbreaks are largely ineffective against these ALM-specific threats. To address this issue, we propose ALMGuard, the first defense framework tailored to ALMs. Based on the assumption that safety-aligned shortcuts naturally exist in ALMs, we design a method to identify universal Shortcut Activation Perturbations (SAPs) that serve as triggers that activate the safety shortcuts to safeguard ALMs at inference time. To better sift out effective triggers while preserving the model's utility on benign tasks, we further propose Mel-Gradient Sparse Mask (M-GSM), which restricts perturbations to Mel-frequency bins that are sensitive to jailbreaks but insensitive to speech understanding. Both theoretical analyses and empirical results demonstrate the robustness of our method against both seen and unseen attacks. Overall, \MethodName reduces the average success rate of advanced ALM-specific jailbreak attacks to 4.6% across four models, while maintaining comparable utility on benign benchmarks, establishing it as the new state of the art. Our code and data are available at https://github.com/WeifeiJin/ALMGuard.

Weifei Jin, Xilong Wang, Wei Zou et al.

Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge database. When a user issues a question targeted by the attack, the RAG system may retrieve these malicious documents, whose injected prompts mislead it into generating attacker-specified answers, thereby compromising the integrity of the RAG system. In this work, we propose CleanBase, a method to detect malicious documents within a knowledge database. Our key insight is that malicious documents crafted for the same attack-targeted questions often exhibit high semantic similarity, as attackers deliberately make them consistent to improve attack success rates. Accordingly, CleanBase constructs a similarity graph over the knowledge database, where each node represents a document and an edge connects two nodes if their semantic similarity--computed using an embedding model--exceeds a statistically determined threshold. Due to their inherent similarity, malicious documents tend to form cliques within this graph. CleanBase detects such cliques and flags the corresponding documents as malicious. We theoretically derive upper bounds on CleanBase's false positive and false negative rates and empirically validate its effectiveness. Experimental results across multiple datasets and prompt injection attacks demonstrate that CleanBase accurately detects malicious documents and effectively safeguards RAG systems. Our source code is available at https://github.com/WeifeiJin/CleanBase.

Suyang Sun, Weifei Jin, Yuxin Cao et al.

Modern Voice Control Systems (VCS) rely on the collaboration of Automatic Speech Recognition (ASR) and Speaker Recognition (SR) for secure interaction. However, prior adversarial attacks typically target these tasks in isolation, overlooking the coupled decision pipeline in real-world scenarios. Consequently, single-task attacks often fail to pose a practical threat. To fill this gap, we first utilize gradient analysis to reveal that ASR and SR exhibit no inherent conflicts. Building on this, we propose Dual-task Universal Adversarial Perturbation (DUAP). Specifically, DUAP employs a targeted surrogate objective to effectively disrupt ASR transcription and introduces a Dynamic Normalized Ensemble (DNE) strategy to enhance transferability across diverse SR models. Furthermore, we incorporate psychoacoustic masking to ensure perturbation imperceptibility. Extensive evaluations across five ASR and six SR models demonstrate that DUAP achieves high simultaneous attack success rates and superior imperceptibility, significantly outperforming existing single-task baselines.

Kun Wang, Guibin Zhang, Zhenhong Zhou et al. · mit

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

Weifei Jin, Yuxin Cao, Junjie Su et al.

In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies have illustrated that surreptitiously crafting adversarial perturbations enables the manipulation of speech recognition systems, resulting in the production of malicious commands. These attack methods mostly require adding noise perturbations under $\ell_p$ norm constraints, inevitably leaving behind artifacts of manual modifications. Recent research has alleviated this limitation by manipulating style vectors to synthesize adversarial examples based on Text-to-Speech (TTS) synthesis audio. However, style modifications based on optimization objectives significantly reduce the controllability and editability of audio styles. In this paper, we propose an attack on ASR systems based on user-customized style transfer. We first test the effect of Style Transfer Attack (STA) which combines style transfer and adversarial attack in sequential order. And then, as an improvement, we propose an iterative Style Code Attack (SCA) to maintain audio quality. Experimental results show that our method can meet the need for user-customized styles and achieve a success rate of 82% in attacks, while keeping sound naturalness due to our user study.

Weifei Jin, Yuxin Cao, Junjie Su et al.

The widespread application of automatic speech recognition (ASR) supports large-scale voice surveillance, raising concerns about privacy among users. In this paper, we concentrate on using adversarial examples to mitigate unauthorized disclosure of speech privacy thwarted by potential eavesdroppers in speech communications. While audio adversarial examples have demonstrated the capability to mislead ASR models or evade ASR surveillance, they are typically constructed through time-intensive offline optimization, restricting their practicality in real-time voice communication. Recent work overcame this limitation by generating universal adversarial perturbations (UAPs) and enhancing their transferability for black-box scenarios. However, they introduced excessive noise that significantly degrades audio quality and affects human perception, thereby limiting their effectiveness in practical scenarios. To address this limitation and protect live users' speech against ASR systems, we propose a novel framework, AudioShield. Central to this framework is the concept of Transferable Universal Adversarial Perturbations in the Latent Space (LS-TUAP). By transferring the perturbations to the latent space, the audio quality is preserved to a large extent. Additionally, we propose target feature adaptation to enhance the transferability of UAPs by embedding target text features into the perturbations. Comprehensive evaluation on four commercial ASR APIs (Google, Amazon, iFlytek, and Alibaba), three voice assistants, two LLM-powered ASR and one NN-based ASR demonstrates the protection superiority of AudioShield over existing competitors, and both objective and subjective evaluations indicate that AudioShield significantly improves the audio quality. Moreover, AudioShield also shows high effectiveness in real-time end-to-end scenarios, and demonstrates strong resilience against adaptive countermeasures.

Weifei Jin, Junjie Su, Hejia Wang et al.

With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models, resulting in a lack of transferability. In real-world scenarios, attackers often cannot access detailed information about the target model, making query-based attacks unfeasible. To address this challenge, we propose a technique called Acoustic Representation Optimization that aligns adversarial perturbations with low-level acoustic characteristics derived from speech representation models. Rather than relying on model-specific, higher-layer abstractions, our approach leverages fundamental acoustic representations that remain consistent across diverse ASR architectures. By enforcing an acoustic representation loss to guide perturbations toward these robust, lower-level representations, we enhance the cross-model transferability of adversarial examples without degrading audio quality. Our method is plug-and-play and can be integrated with any existing attack methods. We evaluate our approach on three modern ASR models, and the experimental results demonstrate that our method significantly improves the transferability of adversarial examples generated by previous methods while preserving the audio quality.

Haolang Lu, Hongrui Peng, Guoshun Nan et al.

Binary malware summarization aims to automatically generate human-readable descriptions of malware behaviors from executable files, facilitating tasks like malware cracking and detection. Previous methods based on Large Language Models (LLMs) have shown great promise. However, they still face significant issues, including poor usability, inaccurate explanations,and incomplete summaries, primarily due to the obscure pseudocode structure and the lack of malware training summaries. Further, calling relationships between functions, which involve the rich interactions within a binary malware, remain largely underexplored. To this end, we propose MALSIGHT, a novel code summarization framework that can iteratively generate descriptions of binary malware by exploring malicious source code and benign pseudocode. Specifically, we construct the first malware summary dataset, MalS and MalP, using an LLM and manually refine this dataset with human effort. At the training stage, we tune our proposed MalT5, a novel LLM-based code model, on the MalS and benign pseudocode datasets. Then, at the test stage, we iteratively feed the pseudocode functions into MalT5 to obtain the summary. Such a procedure facilitates the understanding of pseudocode structure and captures the intricate interactions between functions, thereby benefiting summaries' usability, accuracy, and completeness. Additionally, we propose a novel evaluation benchmark, BLEURT-sum, to measure the quality of summaries. Experiments on three datasets show the effectiveness of the proposed MALSIGHT. Notably, our proposed MalT5, with only 0.77B parameters, delivers comparable performance to much larger Code-Llama.