相关论文: Same Model, Different Weakness: How Language and M…

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly…

Identifying offensive language is essential for maintaining safety and sustainability in the social media era. Though large language models (LLMs) have demonstrated encouraging potential in social media analytics, they lack thorough…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as…

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

In perpetrator treatment, a recurring observation is the dissociation between insight and action: offenders articulate remorse yet behavioral change does not follow. We report four preregistered studies (1,584 multi-agent simulations across…

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…