Related papers: High-Entropy Tokens as Multimodal Failure Points i…

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…

With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks promotes system robustness improvement and neural networks…

Large language model safety is usually assessed with static benchmarks, but key failures are dynamic: value drift under distribution shift, jailbreak attacks, and slow degradation of alignment in deployment. Building on a recent Second Law…

Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal capabilities, but they inherit the tendency to hallucinate from their underlying language models. While visual contrastive decoding has been proposed to mitigate…

Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key to…

Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently, understanding training-data leakage in these systems is increasingly critical. Log-probability-based…

Automated detection of software vulnerabilities is critical for enhancing security, yet existing methods often struggle with the complexity and diversity of modern codebases. In this paper, we introduce EnStack, a novel ensemble stacking…

Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective…

Logit-based LLM watermarking traces and verifies AI-generated content by maintaining green and red token lists and increasing the likelihood of green tokens during generation. However, it fails in low-entropy scenarios, where predictable…

Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…

Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Recent reasoning large language models (LLMs), such as OpenAI o1 and DeepSeek-R1, exhibit strong performance on complex tasks through test-time inference scaling. However, prior studies have shown that these models often incur significant…

Large language models (LLMs) augmented with multi-step reasoning and action generation abilities have shown promise in leveraging external tools to tackle complex tasks that require long-horizon planning. However, existing approaches either…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

Vision-Language Models (VLMs) are increasingly used as perceptual modules for visual content reasoning, including through captioning and DeepFake detection. In this work, we expose a critical vulnerability of VLMs when exposed to subtle,…

Hallucination in large language models (LLMs) can be detected by assessing the uncertainty of model outputs, typically measured using entropy. Semantic entropy (SE) enhances traditional entropy estimation by quantifying uncertainty at the…

Adversarial attacks are known to succeed on classifiers, but it has been an open question whether more complex vision systems are vulnerable. In this paper, we study adversarial examples for vision and language models, which incorporate…

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world…