Related papers: Steering Beyond the Support: Adversarial Training …
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,…
This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful queries disguised by…
Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…
Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new…
Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…
As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…
Adversarial lateral movement via compromised accounts remains difficult to discover via traditional rule-based defenses because it generally lacks explicit indicators of compromise. We propose a behavior-based, unsupervised framework…
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…
Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and…
Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…
Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering,…
Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…
Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from…
Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…
Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic evolution of risk during decoding. This oversight leaves risk signals embedded in decoding…
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…
Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a substantial threat to LLM security. Current strategies for…
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…
Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new…
Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…