Related papers: GUARD-SLM: Token Activation-Based Defense Against …

With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to…

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…

Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within jailbreak prompts. While existing defenses primarily focus on mitigating the effects of jailbreak prompts, they often prove inadequate as jailbreak…

Prompt injection (both direct and indirect) and jailbreaking are now recognized as significant issues for large language models (LLMs), particularly due to their potential for harm in application-integrated contexts. This extended abstract…

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation…

Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts…

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…

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…

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Large Language Models (LLMs) have rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts…

Safety is a paramount concern for large language models (LLMs) in open deployment, motivating the development of safeguard methods that enforce ethical and responsible use through safety alignment or guardrail mechanisms. Jailbreak attacks…

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…

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

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,…

Safety alignment is critical for LLM-powered systems. While recent LLM-powered guardrail approaches such as LlamaGuard achieve high detection accuracy of unsafe inputs written in English (e.g., ``How to create a bomb?''), they struggle with…

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

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…