Related papers: SafeDecoding: Defending against Jailbreak Attacks …
We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…
In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model internal information or have limitations when exploring the unsafe…
Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable…
The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…
With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…
Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concerns about the safety…
Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…
Large language models (LLMs) have demonstrated remarkable capabilities, but their power comes with significant security considerations. While extensive research has been conducted on the safety of LLMs in chat mode, the security…
Large language models (LLMs) are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents, significantly expanding their capabilities while introducing increasingly severe security risks. This paper presents a…
Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…
Jailbreak attacks on large language models (LLMs) involve inducing these models to generate harmful content that violates ethics or laws, posing a significant threat to LLM security. Current jailbreak attacks face two main challenges: low…
Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…
Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose significant security threats. Some defenses have been proposed…
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…
Secure coding is a critical yet often overlooked practice in software development. Despite extensive awareness efforts, real-world adoption remains inconsistent due to organizational, educational, and technical barriers. This paper provides…
As Large Language Models (LLMs) are increasingly being deployed in safety-critical applications, their vulnerability to potential jailbreaks -- malicious prompts that can disable the safety mechanism of LLMs -- has attracted growing…
Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsafe behavior can be induced through semantics, acoustic style, signal artifacts, or internal…
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…
Logging code plays an important role in software systems by recording key events and behaviors, which are essential for debugging and monitoring. However, insecure logging practices can inadvertently expose sensitive information or enable…