Related papers: When Prompt Optimization Becomes Jailbreaking: Ada…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iterations to…

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…

The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to be brief and vague, thereby significantly limiting the full…

As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It tests LLMs with adversarial prompts to uncover…

Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to align multimodal information (visual and auditory) with…

Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities. However, concerns about their trustworthiness remain unresolved, particularly in addressing…

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

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.…

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

Large language models (LLMs) generate human-aligned content under certain safety constraints. However, the current known technique ``jailbreak prompt'' can circumvent safety-aligned measures and induce LLMs to output malicious content.…

System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…

Ensuring the safety of large language model (LLM) applications is essential for developing trustworthy artificial intelligence. Current LLM safety benchmarks have two limitations. First, they focus solely on either discriminative or…

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…