cs.CR · 2026-11-16 · No. 173
Cryptography and Security, 2026-11-16.
5 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
5 entries-
01
PrivacyPR: A Dataset of Real-World Privacy Fixes for Benchmarking Privacy-Aware Code Review
Hua Yang, Aditya Bhardwaj, Shidong Pan, Bowen Xu
cs.CR · cs.AI · cs.SE
Coding agents increasingly review code, yet whether they catch the privacy defects that laws such as the GDPR require software to avoid remains largely untested, partly because few datasets connect real privacy defects to their accepted fixes and review context. We present PrivacyPR, a dataset of 4,131 merged GitHub pull requests (PRs) from 1,469 repositories, created between June 2018 and January 2024. Each PR includes its commits, diffs,...
-
02
From Bytes to Behavior: Request-Level Attribution from Live GPU Hidden States
Jonathan Pan, Yidi Yuan, Xin Wei Chia, Xinhui Su, Vincent Tan, Brenda Ong
cs.CR · cs.AI
Existing memory forensics for machine learning systems typically targets static artifacts, such as model weights or prompt logs, rather than the transient computational states of a live inference process. This gap limits an examiner's ability to analyze the specific behavior of a running large language model (LLM) service that cannot be restarted or modified. We present a method for acquiring per-layer residual-stream activations from a live...
-
03
Beyond Bot Labels: Retrospective Consequence-Grounded Ranking of Attributed Cache Harm in E-Commerce Logs
Jisoo Kim, Youngwoo Seo, Seonghoon Jeong
cs.CR · cs.LG · cs.NI
Web caches reduce origin load and latency, but automated traffic can either warm them or evict objects shoppers reuse, lowering the cache hit ratio (CHR). Existing bot defenses generally infer automation from User-Agent (UA) strings or behavior rather than identify sessions that impose cross-session cache harm. We instead formulate the task as ranking sessions by eviction damage and propose consequence-grounded session ranking. A single...
-
04
Condensing Law of Security Information
Qi Tan, Tianyu Cui, Qi Li, Ke Xu
cs.CR · cs.AI · cs.LG
Scaling laws indicate that the generalization error of a large language model (LLM) decreases monotonically with model size once data is sufficient, and the corollary that larger models outperform smaller ones is now widely accepted. We argue that this corollary fails in security: decisions there hinge on anomalous inputs, which are long-tailed (e.g., zero-day attacks) and therefore poorly served by likelihood fitting. Worse still, the...
-
05
Securing Multi-Agent Systems by Design
Xilong Wang, Xiaoxing Chen, Neil Gong
cs.CR · cs.AI · cs.CL
Multi-agent systems solve complex tasks by decomposing them into subtasks, delegating the subtasks to agents, and aggregating the agents' responses using an aggregation rule. Malicious agents can manipulate the final solution by providing malicious responses to their assigned subtasks. In this paper, we first propose response manipulation attacks (ReMA), which iteratively optimize malicious responses to maximize attack effectiveness....
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.