cs.CR · 2026-08-24 · No. 94

Cryptography and Security, 2026-08-24.

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

Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking

Arulnidhi Karunanidhi

cs.CR · cs.AI

Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future sessions that match it. We measure the cost of this failure mode using plainly worded false assertions generated in a single pass, with no instruction, trigger, or retriever optimization. Poisoning 1.2% of a LongMemEval corpus reduces accuracy from 0.850 to 0.300. A four-stage write-time screening pipeline that reaches 0.832...

arxiv.org/abs/2608.21230 · PDF
02

AID-Guard: Stateful Authorization for Delegated Agent Effects

Yingzhe Tong, Leyu Dai, Songhui Guo

cs.CR · cs.AI

Tool-using AI agents turn delegated tasks into provider effects, yet authorization often ends at admission while provider state, delivery, retry, and recovery evolve. A request may change before commit, or response loss may cause a replacement to create a second effect from one approval. We present AID-Guard, a stateful authorization-to-effect closure protocol. It revalidates the approved request and provider state at commit, retains one...

arxiv.org/abs/2608.21159 · PDF
03

ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

Kai Wang, Zeming Wei, BiaoJie Zeng, Chang Jin, An Wang, Xiaokun Luan, Zhixiao Lin, Jingjing Qu, Xia Hu, Xingcheng Xu

cs.CR · cs.AI

As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise. We argue that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and post-action...

arxiv.org/abs/2608.21101 · PDF
04

$Z^2$-ACT: End-to-End Verifiable Agentic Intent Control for Open 6G RAN

Sunder Ali Khowaja, Kapal Dev, George C. Alexandropoulos

cs.CR · cs.AI · cs.NI

With the progression in open and disaggregated 6G radio access networks, it is expected that the system will be able to host multi-vendors. In order to host multi-vendors, it is essential that AI-assisted control loops remain safe, verifiable, and auditable under concurrent operator intents and untrusted model inputs. The existing studies address the agentic coordination, formal intent constraints, zero-trust prompt verification and...

arxiv.org/abs/2608.21049 · PDF
05

Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making

Pasquale Malacaria, Yunxiao Zhang

cs.CR · cs.AI

Large language models (LLMs) are increasingly used in cybersecurity workflows, yet it remains unclear whether they can perform structured security reasoning or merely rely on superficial cues and prior knowledge. We study this question in the context of defence selection over attack graphs derived from real-world threat scenarios, including ransomware, supply-chain compromise, cloud abuse, Kubernetes attacks, POS malware, and ICS/OT...

arxiv.org/abs/2608.20966 · PDF
06

Vibe Coding and Web Application Security: A Twin-Prompt Study

Darko Andročec

cs.CR · cs.AI

Large language models increasingly generate complete web applications from natural-language prompts, raising the question of whether explicitly requesting security best practice improves the result. We study six functionally distinct web applications, each generated in two prompt variants that are identical except for an appended security-requirements section: a baseline (A) and a security-aware (B) variant. All twelve programs were produced...

arxiv.org/abs/2608.20963 · PDF
07

ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection

Chunyi Wang, Yunfei Ke, Junfeng Yang, Yun-Yun Tsai, Penghui Li

cs.CR · cs.AI

Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based static analyzers (e.g., CodeQL) encode vulnerable code patterns in detection queries and match them against source code. However, existing queries still suffer from false positives (FPs, incorrectly flagging benign code as vulnerable) and false negatives (FNs, missing real vulnerabilities). We present ARQ, an agentic framework that...

arxiv.org/abs/2608.20637 · PDF
08

Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning

Xinyun Liu, Zhi Lu, Yu Chen, Ronghua Xu

cs.CR · cs.LG

Federated learning (FL) is vulnerable to multi-level attacks. However, existing methods address them separately, leaving FL exposed to data leakage, unauthorized reuse, and malicious gradient manipulation. In this work, we propose an FL framework that couples keyed context-provenance watermarking with verifiable lattice-based secure aggregation of Real-World Anchored Watermarking and Lattice-Based Zero-Knowledge Secure Aggregation. At the...

arxiv.org/abs/2608.20580 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.