English
Related papers

Related papers: CommandSans: Securing AI Agents with Surgical Prec…

200 papers

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…

Computation and Language · Computer Science 2024-10-30 Yutao Mou , Shikun Zhang , Wei Ye

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…

Computation and Language · Computer Science 2024-10-18 Leon Zhou , Junfeng Yang , Chengzhi Mao

System prompt configuration can make the difference between near-total phishing blindness and near-perfect detection in LLM email agents. We present PhishNChips, a study of 11 models under 10 prompt strategies, showing that prompt-model…

Cryptography and Security · Computer Science 2026-03-27 Ron Litvak

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety. However, currently known techniques presume that corpora…

Computation and Language · Computer Science 2024-06-10 Fengqing Jiang , Zhangchen Xu , Luyao Niu , Zhen Xiang , Bhaskar Ramasubramanian , Bo Li , Radha Poovendran

Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However, LLM-empowered applications are vulnerable to Indirect Prompt Injection (IPI) attacks, where…

Cryptography and Security · Computer Science 2025-12-12 Yinan Zhong , Qianhao Miao , Yanjiao Chen , Jiangyi Deng , Yushi Cheng , Wenyuan Xu

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

Tool-using LLM agents must act on untrusted webpages, emails, files, and API outputs while issuing privileged tool calls. Existing defenses often mediate trust at the granularity of an entire tool invocation, forcing a brittle choice in…

Cryptography and Security · Computer Science 2026-05-13 Linfeng Fan , Ziwei Li , Yuan Tian , Yichen Wang , Rongsheng Li , Xiong Wang

Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications, which perform text-based tasks by utilizing their advanced language understanding capabilities. However, as LLMs have improved, so have the attacks…

Cryptography and Security · Computer Science 2024-09-27 Sizhe Chen , Julien Piet , Chawin Sitawarin , David Wagner

The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in…

Cryptography and Security · Computer Science 2025-12-30 Toqeer Ali Syed , Mohammad Riyaz Belgaum , Salman Jan , Asadullah Abdullah Khan , Saad Said Alqahtani

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Cryptography and Security · Computer Science 2025-07-15 Joshua Kazdan , Abhay Puri , Rylan Schaeffer , Lisa Yu , Chris Cundy , Jason Stanley , Sanmi Koyejo , Krishnamurthy Dvijotham

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Machine Learning · Computer Science 2026-02-02 Jiawei Li

AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email,…

Cryptography and Security · Computer Science 2026-05-26 Lei Zhao , Abhay Bhaskar , Edgar Dobriban

Prompt injection attacks pose a significant challenge to the safe deployment of Large Language Models (LLMs) in real-world applications. While prompt-based detection offers a lightweight and interpretable defense strategy, its effectiveness…

Cryptography and Security · Computer Science 2025-10-10 Ting-Chun Liu , Ching-Yu Hsu , Kuan-Yi Lee , Chi-An Fu , Hung-yi Lee

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

Cryptography and Security · Computer Science 2026-04-17 Zhengxian Wu , Juan Wen , Wanli Peng , Haowei Chang , Yinghan Zhou , Yiming Xue

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…

Cryptography and Security · Computer Science 2026-04-22 Dongcheng Zhang , Yiqing Jiang

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Computation and Language · Computer Science 2025-12-16 Cheng Wang , Zeming Wei , Qin Liu , Muhao Chen

Large language models (LLMs) have been widely deployed as the backbone with additional tools and text information for real-world applications. However, integrating external information into LLM-integrated applications raises significant…

Cryptography and Security · Computer Science 2024-11-27 Jiongxiao Wang , Fangzhou Wu , Wendi Li , Jinsheng Pan , Edward Suh , Z. Morley Mao , Muhao Chen , Chaowei Xiao

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this…

Cryptography and Security · Computer Science 2025-10-03 Yinuo Liu , Ruohan Xu , Xilong Wang , Yuqi Jia , Neil Zhenqiang Gong