23 accepted papers
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when executing hazardous instructions. Current safety evaluation
Recently, Large Vision-Language Models (LVLMs) have been demonstrated to be vulnerable to jailbreak attacks, highlighting the urgent need for further research to comprehensively identify and mitigate these threats. Unfortunately, existing jailbreak studies primarily focus on coarse-grained input man
The generation of safety-critical scenarios in simulation has become increasingly crucial for safety evaluation in autonomous vehicles (AV) prior to road deployment in society. However, current approaches largely rely on predefined threat patterns or rule-based strategies, which limit their ability
As the pretraining-finetuning paradigm becomes dominant in modern AI, the security of model supply chains faces new risks from backdoor attacks. Existing work primarily studies backdoors injected during pretraining and treats subsequent finetuning with clean data as a defense, while recent finetunin
Post-training quantization (PTQ) offers an efficient approach to compressing large language models (LLMs), significantly reducing memory access and computational costs. Existing compensation-based weight calibration methods often rely on a second-order Taylor expansion to model quantization error, u
Hallucination has emerged as a pivotal challenge of Large Language Models (LLMs) that generate plausible yet non‑factual content, significantly impeding the trustworthy AI applications in real-world scenarios like medical diagnosis and autonomous driving. Editing the internal activations of LLMs du
With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to severe accuracy degradation, hindering the quantiz…
Recently, semantically constrained adversarial examples (SemanticAE), which are directly generated from natural language instructions, have become a promising avenue for future research due to their flexible attacking forms, but have not been thoroughly explored yet. To generate SemanticAEs, current…
There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient atta…
Though achieving significant success in personalized image synthesis, Latent Diffusion Models (LDMs) pose substantial social risks caused by unauthorized misuse (e.g., face theft). To counter these threats, the Anti-Customization (AC) method that exploits adversarial perturbations was proposed. Unfo…
Retrieval-Augmented Generation (RAG) has proven effective in enhancing the factuality of LLMs’ generation, making them a focal point of research. However, previous RAG approaches overlook the lexical diversity of queries, hindering their ability to achieve a granular relevance assessment between que…
Intervening the internal activations of large language models (LLMs) provides an effective inference-time alignment approach to mitigate undesirable behaviors, such as generating erroneous or harmful content, thereby ensuring safe and reliable applications of LLMs. However, previous methods neglect
Deepfake detection is increasingly crucial due to the rapid rise of AI-generated content. Existing methods achieve high performance relying on computationally intensive large models, making real-time detection on resource-constrained edge devices challenging. Given that deepfake detection is a binar
Diffusion models (DMs) have been significantly developed and widely used in various applications due to their excellent generative qualities. However, the expensive computation and massive parameters of DMs hinder their practical use in resource-constrained scenarios. As one of the effective compres…
In this study, we explore the robustness of cooperative multi-agent reinforcement learning (c-MARL) against Byzantine failures, where any agent can enact arbitrary, worst-case actions due to malfunction or adversarial attack. To address the uncertainty that any agent can be adversarial, we propose a…
Recently the emergence of naturalistic adversarial patch (NAP) which possesses a deceptive appearance and various representations underscores the necessity of developing robust detection strategies. However existing approaches fail to differentiate the deep-seated natures in adversarial patches i.e.…
While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus drawing increased research attention. However, existing studies o…
Physical world adversarial attack is a highly practical and threatening attack, which fools real world deep learning systems by generating conspicuous and maliciously crafted real world artifacts. In physical world attacks, evaluating naturalness is highly emphasized since human can easily detect an…
To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of modifying models, has attracted intensive attention due to its hig…
Although deep neural networks (DNNs) have already made fairly high achievements and a very wide range of impact, their vulnerability attracts lots of interest of researchers towards related studies about artificial intelligence (AI) safety and robustness this year. A series of works reveals that the…
Deep learning models are vulnerable to adversarial examples. As a more threatening type for practical deep learning systems, physical adversarial examples have received extensive research attention in recent years. However, without exploiting the intrinsic characteristics such as model-agnostic and…
Prohibited items detection in X-ray images often plays an important role in protecting public safety, which often deals with color-monotonous and luster-insufficient objects, resulting in unsatisfactory performance. Till now, there have been rare studies touching this topic due to the lack of specia…
Adversarial examples are inputs with imperceptible perturbations that easily misleading deep neural networks (DNNs). Recently, adversarial patch, with noise confined to a small and localized patch, has emerged for its easy feasibility in real-world scenarios. However, existing strategies failed to g…