相关论文: Universal Jailbreak Suffixes Are Strong Attention …
A novel hack involving Large Language Models (LLMs) has emerged, exploiting adversarial suffixes to deceive models into generating perilous responses. Such jailbreaks can trick LLMs into providing intricate instructions to a malicious user…
Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…
Gradient-based adversarial prompting, such as the Greedy Coordinate Gradient (GCG) algorithm, has emerged as a powerful method for jailbreaking large language models (LLMs). In this paper, we present a systematic appraisal of GCG and its…
Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among…
Many recent studies showed that LLMs are vulnerable to jailbreak attacks, where an attacker can perturb the input of an LLM to induce it to generate an output for a harmful question. In general, existing jailbreak techniques either optimize…
Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks that attempt to bypass guardrails via adversarial prompts. Among existing approaches, the Greedy…
Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to prompt injection attacks, where injected secondary prompts force the model to deviate from the user's…
Goal hijacking is a type of adversarial attack on Large Language Models (LLMs) where the objective is to manipulate the model into producing a specific, predetermined output, regardless of the user's original input. In goal hijacking, an…
Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…
As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…
Jailbreak attacks to Large audio-language models (LALMs) are studied recently, but they exclusively focused on the attack scenario where the adversary can fully manipulate user prompts (named strong adversary) and limited in effectiveness,…
Language models (LMs) are often used as zero-shot or few-shot classifiers by scoring label words, but they remain fragile to adversarial prompts. Prior work typically optimizes task- or model-specific triggers, making results difficult to…
The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties. Recent studies found that attaching…
Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate…
The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common…
Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve high attack performance while being too cumbersome and…
Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…
Large Language Models (LLMs) have achieved remarkable success across diverse tasks, yet they remain vulnerable to adversarial attacks, notably the well-known jailbreak attack. In particular, the Greedy Coordinate Gradient (GCG) attack has…
Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and…
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,…