相关论文: Secure Tug-of-War (SecTOW): Iterative Defense-Atta…

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities. This sequential approach creates a mismatch --…

Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters. Newer LLM-based filters detect latent intent beyond keywords, making token-level…

Traditional security protection methods struggle to address sophisticated attack vectors in large-scale distributed systems, particularly when balancing detection accuracy with data privacy concerns. This paper presents a novel distributed…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which…

Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, policy-centric loop, causing attack discovery to suffer from…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…

Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper, we reveal a critical safety inconsistency: LLMs can more…

Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks. Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the…

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense -- falsely flagging benign inputs as…

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities that increasingly influence various aspects of our daily lives, constantly defining the new boundary of Artificial General Intelligence (AGI). Image modalities,…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. To investigate this gap, we introduce a dataset of 3,000…

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse…