English
Related papers

Related papers: MemLineage: Lineage-Guided Enforcement for LLM Age…

200 papers

Agent-assisted memory recall is one critical research problem in the field of human-computer interaction. In conventional methods, the agent can retrieve information from its equipped memory module to help the person recall incomplete or…

Artificial Intelligence · Computer Science 2025-08-01 Qian Zhao , Zhuo Sun , Bin Guo , Zhiwen Yu

Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and…

Cryptography and Security · Computer Science 2026-05-22 Sidnei Barbieri , Ágney Lopes Roth Ferraz , Lourenço Alves Pereira Júnior

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen

Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over…

Artificial Intelligence · Computer Science 2026-04-07 Shu Wang , Edwin Yu , Oscar Love , Tom Zhang , Tom Wong , Steve Scargall , Charles Fan

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Cryptography and Security · Computer Science 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Cryptography and Security · Computer Science 2026-02-09 Sizhe Chen , Arman Zharmagambetov , David Wagner , Chuan Guo

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Cryptography and Security · Computer Science 2026-05-14 Priyal Deep , Shane Emmons , Amy Fox , Kyle Bacon , Kelley McAllister , Peter Ortiz , Krisztian Flautner

Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such as prompt injection or memory poisoning. In deployment,…

Artificial Intelligence · Computer Science 2026-05-19 Ahmad Al-Tawaha , Shangding Gu , Peizhi Niu , Ruoxi Jia , Ming Jin

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence…

Cryptography and Security · Computer Science 2026-01-13 Balachandra Devarangadi Sunil , Isheeta Sinha , Piyush Maheshwari , Shantanu Todmal , Shreyan Mallik , Shuchi Mishra

Agent memory failures are silent: an LLM-based agent can produce a fluent response even when it fails to extract, retain, or retrieve the information needed across sessions. The write-manage-read loop describes the external pipeline of…

Artificial Intelligence · Computer Science 2026-05-08 Xutao Mao , Jinman Zhao , Gerald Penn , Cong Wang

Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or biased memory accumulation can trigger abnormal agent…

Computation and Language · Computer Science 2026-05-22 Weiwei Xie , Shaoxiong Guo , Fan Zhang , Tian Xia , Xue Yang , Lizhuang Ma , Junchi Yan , Qibing Ren

Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, this memory mechanism also creates a practical security…

Artificial Intelligence · Computer Science 2026-05-25 Zhewen Tan , Yilun Yao , Huiyan Jin , Wenhan Yu , Guoan Wang , Mengyuan Fan , liang lu , Feng Liu , Xiangzheng Zhang , Duohe Ma , Tong Yang , Lin Sun

LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments, adversaries can copy and reuse these prompts with other…

Cryptography and Security · Computer Science 2026-05-20 Qinfeng Li , Yuntai Bao , Jianghui Hu , Wenqi Zhang , Jintao Chen , Huifeng Zhu , Yier Jin , Xuhong Zhang

When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers…

Cryptography and Security · Computer Science 2025-08-15 Pallavi Zambare , Venkata Nikhil Thanikella , Ying Liu

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Cryptography and Security · Computer Science 2026-04-15 Yulin Chen , Tri Cao , Haoran Li , Yue Liu , Yibo Li , Yufei He , Le Minh Khoi , Yangqiu Song , Shuicheng Yan , Bryan Hooi

Large Language Model (LLM)-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and effective defenses remain lacking. In this paper, we propose…

Cryptography and Security · Computer Science 2026-02-10 Yuhao Wang , Shengfang Zhai , Guanghao Jin , Yinpeng Dong , Linyi Yang , Jiaheng Zhang

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhanced ability to interact with external systems and process…

Cryptography and Security · Computer Science 2024-12-24 Feiran Jia , Tong Wu , Xin Qin , Anna Squicciarini

The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, current defenses are…

Cryptography and Security · Computer Science 2025-10-13 Debeshee Das , Luca Beurer-Kellner , Marc Fischer , Maximilian Baader

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…

Cryptography and Security · Computer Science 2026-01-12 Akshaj Prashanth Rao , Advait Singh , Saumya Kumaar Saksena , Dhruv Kumar