相关论文: Human-Interpretable Adversarial Prompt Attack on L…

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable…

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning…

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods…

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…

The critical challenge of prompt injection attacks in Large Language Models (LLMs) integrated applications, a growing concern in the Artificial Intelligence (AI) field. Such attacks, which manipulate LLMs through natural language inputs,…

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

Security threats like prompt injection attacks pose significant risks to applications that integrate Large Language Models (LLMs), potentially leading to unauthorized actions such as API misuse. Unlike previous approaches that aim to detect…

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

Large Language Models (LLMs) are vulnerable to prompt injection attacks, and several defenses have recently been proposed, often claiming to mitigate these attacks successfully. However, we argue that existing studies lack a principled…

The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…

Current research on operator control of Large Language Models improves model robustness against adversarial attacks and misbehavior by training on preference examples, prompting, and input/output filtering. Despite good results, LLMs remain…

Large language models have gained widespread prominence, yet their vulnerability to prompt injection and other adversarial attacks remains a critical concern. This paper argues for a security-by-design AI paradigm that proactively mitigates…

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…