相关论文: Directional Embedding Smoothing for Robust Vision …

Large Language Models (LLMs) have achieved remarkable success across domains such as healthcare, education, and cybersecurity. However, this openness also introduces significant security risks, particularly through embedding space…

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

Sentence representations are foundational to many Natural Language Processing (NLP) applications. While recent methods leverage Large Language Models (LLMs) to derive sentence representations, most rely on final-layer hidden states, which…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize…

Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary…

Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical ``modality collapse'' phenomenon…

Recent provably secure linguistic steganography (PSLS) methods rely on mainstream autoregressive language models (ARMs) to address historically challenging tasks, that is, to disguise covert communication as ``innocuous'' natural language…

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models…

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Aligned language models face a significant limitation as their fine-tuning often results in compromised safety. To tackle this, we propose a simple method RESTA that performs LLM safety realignment. RESTA stands for REstoring Safety through…

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…

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power autonomous agents. Prior work typically focus on maximizing attack success rate (ASR) but…

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…

The emergence of vision-language-action models (VLAs) for end-to-end control is reshaping the field of robotics by enabling the fusion of multimodal sensory inputs at the billion-parameter scale. The capabilities of VLAs stem primarily from…