Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning

Large language model (LLM) agents are increasingly deployed in multi-agent systems (MAS) to accomplish complex tasks. Pr

历史摘要 · 未重新核验 · arXiv cs.CR

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt inje

历史摘要 · 未重新核验 · arXiv cs.CR

How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery

How much does an agent harness affect vulnerability discovery, and does its value depend on the model? We study 24 model

历史摘要 · 未重新核验 · arXiv cs.CR

CALLIOPE: Private Insights into AI Use, Without Embeddings

We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g

历史摘要 · 未重新核验 · arXiv cs.CR

Sign Here: Attributing a Source for a More Trustworthy Software Supply Chain

Software supply chain attacks continue to be on the rise, exploiting the trust that helps open source ecosystems thrive.

历史摘要 · 未重新核验 · arXiv cs.CR

A Digital Twin to Improve Cyber-Social Impact

The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has signific

历史摘要 · 未重新核验 · arXiv cs.CR

After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents

Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the syst

历史摘要 · 未重新核验 · arXiv cs.CR

MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems

Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, s

历史摘要 · 未重新核验 · arXiv cs.CR

Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory

Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes i

历史摘要 · 未重新核验 · arXiv cs.CR

ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents

AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that

历史摘要 · 未重新核验 · arXiv cs.CR

Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts

LLMs increasingly operate over mixed-sensitivity contexts, where they must reason over information ranging from public t

历史摘要 · 未重新核验 · arXiv cs.CR

Self-Evolving Static Analysis via LLM Pseudo-Labeling

Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules hav

历史摘要 · 未重新核验 · arXiv cs.CR

Raise or Check? Predicting the Necessity of Additional Fuzzing for Continuous Fuzzing

Continuous fuzzing is used for vulnerability detection in Open Source Software (OSS). Large-scale services such as Googl

历史摘要 · 未重新核验 · arXiv cs.CR

HydraPoT: A Configurable Multi-Agent Framework for Cost-Aware LLM-Assisted Honeypots

Large language models (LLMs) can improve honeypot realism by generating dynamic, context-aware responses, but powerful c

历史摘要 · 未重新核验 · arXiv cs.CR

Pillow: Bundled libopenjp2 2.5.4 in all wheels since 11.1.0 carries OSV-2025-219 heap-buffer-overflow write reachable from Image.open().load()

### Summary Every Pillow wheel from 11.1.0 onward bundles a libopenjp2 containing a heap-buffer-overflow **write** that

历史摘要 · 未重新核验 · GitHub Advisory

[原创]CVE-2020-6507利用链

CVE-2020-6507

[原创]CVE-2020-6507利用链

历史摘要 · 未重新核验 · 看雪

CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报

CVE-2026-39821

CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报

历史摘要 · 未重新核验 · 先知社区

CVE-2026-6791：8 MiB 输入击穿 glibc wordexp 栈

CVE-2026-6791

CVE-2026-6791：8 MiB 输入击穿 glibc wordexp 栈

历史摘要 · 未重新核验 · 先知社区

Critical PHP Vulnerability (CVE-2026-109618, CVE-2026-109619) [infocon yellow], (Wed, Oct 21st)

CVE-2026-109619 · CVE-2026-109618

PHP.net announced that it will release a critical update today. We decided to change the infoCon to YELLOW due to the wi

历史摘要 · 未重新核验 · SANS ISC

OP-Print: Tracing Membership Imprints in On-Policy Self-Distillation

On-policy distillation has been widely adopted for alleviating the distribution mismatch of off-policy distillation. Sel

历史摘要 · 未重新核验 · arXiv cs.CR