English
Related papers

Related papers: When Alignment Isn't Enough: Response-Path Attacks…

200 papers

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

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Multiagent Systems · Computer Science 2024-10-11 Donghyun Lee , Mo Tiwari

This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent. Modern LLM agents operate over an…

Cryptography and Security · Computer Science 2026-05-19 Wenjie Qu , Ming Xu , Peiran Wang , Shengfang Zhai , Jiaheng Zhang , Dawn Song

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…

Computation and Language · Computer Science 2025-11-18 Xikang Yang , Biyu Zhou , Xuehai Tang , Jizhong Han , Songlin Hu

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…

Cryptography and Security · Computer Science 2026-05-01 Luyao Xu , Xiang Chen

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) to mitigate factual hallucinations. Recent paradigms shift from static pipelines to Modular and Agentic RAG frameworks, granting models autonomy for multi-hop…

Information Retrieval · Computer Science 2026-03-03 Yichao Wu , Penghao Liang , Yafei Xiang , Mengwei Yuan , Jianan Liu , Jing Yang , Xianyou Li , Weiran Yan

The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from isolated operation to collaborative ecosystems, we witness the…

Artificial Intelligence · Computer Science 2026-05-20 Yixiang Yao , Yuhang Yao , Xinyi Fan , Jiechao Gao , Jie Wang , Minjia Zhang , Srivatsan Ravi , Carlee Joe-Wong

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Multiagent Systems · Computer Science 2026-04-21 Nokimul Hasan Arif , Qian Lou , Mengxin Zheng

In this work, we present a series of structure transformation attacks on LLM alignment, where we encode natural language intent using diverse syntax spaces, ranging from simple structure formats and basic query languages (e.g., SQL) to new…

Machine Learning · Computer Science 2025-07-04 Shehel Yoosuf , Temoor Ali , Ahmed Lekssays , Mashael AlSabah , Issa Khalil

Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant role, leaving the user role unaligned, and stick to a fixed…

Cryptography and Security · Computer Science 2025-04-08 Erfan Shayegani , G M Shahariar , Sara Abdali , Lei Yu , Nael Abu-Ghazaleh , Yue Dong

Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to automate tasks across diverse apps and workflows. Yet, the security implications of deploying…

Cryptography and Security · Computer Science 2025-11-07 Chenghao Du , Quanfeng Huang , Tingxuan Tang , Zihao Wang , Adwait Nadkarni , Yue Xiao

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

Since the advent of large language models, prompt engineering now enables the rapid, low-effort creation of diverse autonomous agents that are already in widespread use. Yet this convenience raises urgent concerns about the safety,…

Artificial Intelligence · Computer Science 2025-06-27 Daewon Kang , YeongHwan Shin , Doyeon Kim , Kyu-Hwan Jung , Meong Hi Son

Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks.…

Cryptography and Security · Computer Science 2026-02-10 Tianyi Wang , Huawei Fan , Yuanchao Shu , Peng Cheng , Cong Wang

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…

Cryptography and Security · Computer Science 2026-04-14 Xingyu Lyu , Jianfeng He , Ning Wang , Yidan Hu , Tao Li , Danjue Chen , Shixiong Li , Yimin Chen

Previous benchmarks on prompt injection in large language models (LLMs) have primarily focused on generic tasks and attacks, offering limited insights into more complex threats like data exfiltration. This paper examines how prompt…

Cryptography and Security · Computer Science 2025-06-03 Meysam Alizadeh , Zeynab Samei , Daria Stetsenko , Fabrizio Gilardi

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah

A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic…

Systems and Control · Electrical Eng. & Systems 2023-10-09 Kristina Miller , Christopher K. Zeitler , William Shen , Kerianne Hobbs , Sayan Mitra , John Schierman , Mahesh Viswanathan

Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilistic inference,…

Cryptography and Security · Computer Science 2026-02-10 Guanquan Shi , Haohua Du , Zhiqiang Wang , Xiaoyu Liang , Weiwenpei Liu , Song Bian , Zhenyu Guan

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…

Computation and Language · Computer Science 2025-11-24 Ziqi Miao , Lijun Li , Yuan Xiong , Zhenhua Liu , Pengyu Zhu , Jing Shao