cs.CR · 2026-08-11 · No. 81
Cryptography and Security, 2026-08-11.
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
Stealing Reasoning Traces from Proprietary LLM APIs
Alexander Panfilov, David Schmotz, Ilia Shumailov, Luca Beurer-Kellner, Joachim Schaeffer, Ameya Prabhu, Jonas...
cs.CR · cs.AI · cs.LG
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. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are...
-
02
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Puyu Zeng, Simeng Qin, Jingzhi Li, Ju Jia, Zheli Liu, Xiaojun Jia
cs.CR · cs.AI
Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined. This creates a practical blind spot: multiple locally plausible skills may pass security checks while collectively forming a harmful workflow during agent execution. To...
-
03
Activation Probes Surface Code-Security Signals that the Model's Output Misses
Ivan Wiryadi
cs.CR · cs.LG
AI coding agents now write a growing share of production code, and human security review does not scale at the rate code is generated. The agents in widest use are closed-weight, so a deploying team cannot read their internals. It can instead run an open-weight model as a reviewer over the agent's output. That reviewer's activations are readable. We ask whether reading those activations recovers a security signal that simply asking the same...
-
04
RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges
Hanlin Jiang, Puyi Wang, Jiandong Jin, Shaofei Li, Zhan Shen, Pengli Wang, Ziming Wang, Yifeng Cai, Ning Jia, Yuxin...
cs.CR · cs.AI
Real-world cyberattacks often require sustained progress across multiple hosts and network segments, making multi-hop cyber ranges essential infrastructure for studying and improving LLM agents' ability to sustain complete attack chains. Prior work has scaled isolated vulnerability tasks and constructed multi-host scenarios from manually specified vulnerability semantics. However, they are still unable to automatically orchestrate the growing...
-
05
STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
Hanlin Jiang, Jionghao Huang, Shaofei Li, Bojia Yu, Peng Jiang, Yuxin Ren, Ning Jia, Yao Guo, Ding Li
cs.CR · cs.AI
Incident response planning is critical for restoring compromised software systems after cyberattacks. Common practice relies on expert-driven playbooks that encode fixed response procedures, but these static workflows struggle to adapt to evolving incident states, changing recovery objectives, and execution feedback. Recent LLM-based planners and tool-using agents improve automation, yet they remain unstable in long-horizon response because...
-
06
ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents
Hongwei Yao, Yiming Liu, Meihui Chen, Jieling Chen, Zikun Chen, Yiling He, Wangze Ni, Cong Wang, Kui Ren
cs.CR · cs.AI
Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an adversarial variant that preserves its instruction, configuration, initial state, rating model, and...
-
07
Track me if you can: Ephemeral coin tracing
Ignacio Amores-Sesar, Christian Cachin, Rohit Chatterjee, Luiza Soezima, François-Xavier Wicht, Michelle Yeo
cs.CR · cs.DC
Privacy-preserving payment systems are well understood, yet their adoption in regulated settings, such as central bank digital currencies (CBDCs), institutional stablecoins, and other compliant payment infrastructures, has been limited by concerns over their potential misuse for illicit activities. Regulators counter financial crime with a toolbox of complementary measures to identify, trace, and stop criminal actors. Tracing is one key tool:...
-
08
Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference
Tejasvi C. Addagada
cs.CR · cs.AI
The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests. In multi-tenant deployments this cache is shared across tenants, creating a timing side channel: an adversarial tenant can reconstruct another tenant's private prompt by probing cache-hit latency. Three published attacks exploit it -- PROMPTPEEK, EarlyBird and InputSnatch -- reaching up to 100%...
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.