arXiv AI

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching

arXiv:2601. 23088v2 Announce Type: replace-cross Abstract: Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft.

arXiv AI

4d ago

Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning

arXiv:2609.35908v1 Announce Type: cross Abstract: Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely...

By Zihan Zhang, Shuangjie Yao, Zesen Liu, Zhixiang Zhang, Wai Ip Lai, Dung Hiu Hilton Yeung, Chun Kit Zhang, Fuchen Ma, Yuanyuan Yuan, Yu Jiang, Dongdong She

llms rag safety

arXiv AI

Jul 23

HijackKV: New Threat in Position-Independent KV Cache Reuse

arXiv:2607. 19957v1 Announce Type: cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs).

By Yichi Zhang, Zhiqi Wang, Huan Zhang, Yuchen Yang

llms efficiency

arXiv AI

Aug 5

MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM Agents

arXiv:2608. 03844v1 Announce Type: new Abstract: Memory-augmented LLM agents rely on rich context for long-horizon reasoning and acting, yet their memory modules expose a persistent attack surface for malicious records, making the study of memory poisoning threats imperative.

By Jiaming Chen, Yisen Gao, Yanping Li, Zifan Liu, Yumeng Zhang, Jun Zhang

llms agents

arXiv AI

Jun 29

DMind Benchmark: Toward a Holistic Assessment of LLM Capabilities across the Web3 Domain

arXiv:2504. 16116v4 Announce Type: replace-cross Abstract: The Web3 ecosystem, underpinned by cryptographic primitives and decentralized consensus, represents a high-stakes environment where software vulnerabilities and incentive misalignments translate directly into financial loss.

By Enhao Huang, Pengyu Sun, Shuxun Wang, Zixin Lin, Alex Chen, Kaichun Hu, Joey Ouyang, Frank Li, Zhiyu Zhang, Haobo Wang, Yiming Li, Zhan Qin, James Yi, Gang Zhao, Ziang Ling, Lowes Yang

llms benchmarks safety

arXiv AI

Sep 10

Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces

The paper introduces an attack that reconstructs text generated by locally hosted large language models by monitoring CPU cache activity during detokenization. It uses Flush+Reload on shared tokenizer code to time decoding, then Prime+Probe to capture token‑dependent cache traces, followed by a clustering‑and‑language‑model pipeline to recover the output text. The method is evaluated across various datasets, hardware, inference frameworks, and model families, successfully retrieving semantically accurate outputs from real‑world local LLM deployments, including agentic systems.

By Roy Weiss, Benyamin Konstantinov, Eitam Sheetrit, Tomer Simon, Yisroel Mirsky

llms agents nlp

arXiv AI

Sep 1

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors

arXiv:2604.27426v2 Announce Type: replace-cross Abstract: Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although "local...

By Zi Li, Tian Zhou, Wenze Li, Jingyu Hua, Yunlong Mao, Sheng Zhong

llms fine-tuning multimodal safety

arXiv AI

Jun 9

Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems

arXiv:2606. 08661v1 Announce Type: cross Abstract: Data agents integrate LLM-driven reasoning with relational data access, executable analytical tools, and multi-step workflow orchestration, making them increasingly central to enterprise analytics.

By Kuncan Wang, Ziting Wang, Peizhuo Lv, Haoyang Li, Guoliang Li, Gao Cong, Wei Dong

llms agents

arXiv Machine Learning

Jul 16

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge

arXiv:2607. 13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms.

By Ren-Yi Huang, Mingchen Li, Dumindu Samaraweera, Morris Chang

llms efficiency safety

arXiv AI

4d ago

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents

arXiv:2605.01970v4 Announce Type: replace-cross Abstract: Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. Th...

By Debeshee Das, Julien Piet, Darya Kaviani, Luca Beurer-Kellner, Florian Tram\`er, David Wagner

llms rag agents multimodal benchmarks safety

arXiv AI

Jun 24

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

arXiv:2606. 24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts.

By Yuanhe Zhao, Tianyu Zhang, Huafei Xing, Derek F. Wong, Jianbin Li, Tao Fang

llms rag agents safety

arXiv AI

Aug 11

Stealing Reasoning Traces from Proprietary LLM APIs

arXiv:2608. 09867v1 Announce Type: cross Abstract: Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage.

By Alexander Panfilov, David Schmotz, Ilia Shumailov, Luca Beurer-Kellner, Joachim Schaeffer, Ameya Prabhu, Jonas Geiping, Maksym Andriushchenko

llms rag agents efficiency safety

arXiv AI

Jun 12

SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems

arXiv:2606. 12703v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) agents increasingly run with persistent memory that accumulates across user sessions.

By Tarun Sharma

llms rag agents benchmarks safety

Related stories