cs.CR · 2026-08-06 · No. 76
Cryptography and Security, 2026-08-06.
8 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Hardware Design and Security in the Era of Chiplets and LLMs
Johann Knechtel, Ozgur Sinanoglu, Paul V. Gratz, Ramesh Karri
cs.CR · cs.AI · cs.AR
The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) flows. While these paradigms offer unprecedented benefits in yield, modularity, design productivity, etc., they radically expand the hardware attack surface. This paper provides a unified analysis of these frontiers, ranging from attacks on...
-
02
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
Yuxuan Huang, Xingyu Zeng, Tianhang Zheng, Chaochao Lu
cs.CR · cs.AI · cs.CL
Released aligned large language models remain vulnerable to malicious downstream finetuning. Existing defenses are largely designed for the fine-tuning-as-a-service (FTaaS) paradigm or rely on downstream users to follow additional safety procedures, and therefore do not directly address the setting we study: a provider controlled partially protected open-weight (PPOW) release setting in which most weights remain trainable while a small...
-
03
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
Jiaming Cheng, Subhransu Das, Rajiv Ramnath
cs.CR · cs.AI · cs.LG
Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''. That credit is a claim about \emph{which} example's cache is relayed, not merely that one is. We audit it causally in released systems. The cache is replaced with deranged (mismatched-example), zeroed, and moment-matched random counterparts, under two regimes defined by whether the receiver needs the sender's private...
-
04
PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates
Zijian Wang, Yubo Zhu, Muzhi Dong, Yanjun Lou, Yisheng Li, ZiLiang Zhang, Wei Tong, Yuan Zhang, Jingyu Hua, Sheng Zhong
cs.CR · cs.AI
In Retrieval-Augmented Generation (RAG), post-retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages. However, the robustness of this safeguard against knowledge poisoning has not been adequately studied. Existing black-box poisoning methods all assert the target answer in frontal contradiction with what the resolver treats as settled, the very signal these methods are built to detect. We propose PURPOSE, a...
-
05
Breadcrumbing Search Agents
Xuebin Li, Hanqing Zhao, Siyuan Liang, Kejiang Chen, Weiming Zhang, Dacheng Tao, Nenghai Yu
cs.CR · cs.AI · cs.CL
LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web content retrieved during execution is untrusted, exposing agents to prompt injection and goal hijacking. Prior work on search-agent safety primarily focuses on static web-content injection, but modern agents issue follow-up queries and cross-check competing sources, so a single injected...
-
06
DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models
Zhicong Huang, Cheng Hong, Tao Wei
cs.CR · cs.CL · cs.LG
Cloud-based language model services routinely process prompts containing sensitive information. Obfuscation-based defenses---including ObfusLM, SentinelLMs, TextObfuscator, and DPNR---mitigate this risk by transforming prompt representations before transmission, offering a lightweight alternative to cryptographic solutions. We show these defenses provide far less protection than previously believed. We present DeepInvert, a semi-supervised...
-
07
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
Zhaoqi Wang, Daqing He, Zijian Zhang, Ye Liu, Jiamou Liu, Zhirui Zeng, Zhan Qin, Zhen Li, Xin Li, Hongwei Yao,...
cs.CR · cs.AI
While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM outputs. To counter this threat, we propose SecureCollaRAG, a Byzantine-tolerant collaborative RAG framework leveraging Multi-source Knowledge Validation...
-
08
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
Ryozo Masukawa, Ian Bryant, Armita Kazeminajafabadi, Sanggeon Yun, Hyunwoo Oh, SungHeon Jeong, Nathaniel D. Bastian,...
cs.CR · cs.AI · cs.LG · cs.MA
Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied. Meanwhile, recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have improved LLM reasoning, but their integration into cybersecurity remains elusive...
This edition is part of The Daily Abstract — cs.CR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.