按年被提到
20242025 · 2 次2026
AI 安全、伦理与社会影响›模型窃取、记忆与水印·arXiv:2403.04957 · cs.AI

Automatic and Universal Prompt Injection Attacks against Large Language Models

Xiaogeng Liu, Zhiyuan Yu, Yizhe Zhang, Ning Zhang, Chaowei Xiao · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-03-16 · 最近 2025-08-28
2不同的人
2活跃月份
2讨论串
84被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks manipulate LLM-integrated applications into producing responses aligned with the attacker's injected content, deviating from the user's actual requests. The substantial risks posed by these attacks underscore the need for a thorough understanding of the threats. Yet, research in this area faces challenges due to the lack of a unified goal for such attacks and their reliance on manually crafted prompts, complicating comprehensive assessments of prompt injection robustness. We introduce a unified framework for understanding the objectives of prompt injection attacks and present an automated gradient-based method for generating highly effective and universal prompt injection data, even in the face of defensive measures. With only five training samples (0.3% relative to the test data), our attack can achieve superior performance compared with baselines. Our findings emphasize the importance of gradient-based testing, which can avoid overestimation of robustness, especially for defense mechanisms.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论Eridrus · 2025-03

“I applaud you for trying to tackle this, but after reading your docs a little I am skeptical of your approach. Your example of having a rule saying that the user's email address is not put in a search query seems to have two problems: a) non-LLM models can be bypassed by telling LLMs to encode the email tokens, trivially ROT13, or many other encoding sch…”

Strengthening AI Agent Hijacking Evaluations原评论 ↗
被提交为 story · 1 次