CrowdStrike Protects Customers from Threats Delivered via PHP2Shell
CrowdStrike Protects Customers from Threats Delivered via PHP2Shell
2026-10-26 归档
今日共收录 660 条安全情报，包含 0 个 CVE，351 篇安全通告，以及 56 篇研究论文。
← 返回归档列表Why Organizations Secure AI Agents with Falcon GuardianOct 23, 2026
Why Organizations Secure AI Agents with Falcon GuardianOct 23, 2026
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
AI coding agents hijacked using AGENTS.md file in Downloads folder
Researchers found a malicious AGENTS markdown instruction file in a customer's Downloads folder that tricked an AI codin
Trusting the Tool: Asymmetric Deference of LLM Vulnerability Auditors to Static-Analysis Evidence
Pipelines that combine large language models (LLMs) with static analysis let the model consume the analyser's output as
On Task, Off Track: Benchmarking LLM and Agent Robustness to Near-Target Prompt Injection
Prompt injection benchmarks assess whether large language models (LLMs) and agents resist malicious instructions embedde
DeepAVR: Deep Analysis via Multi-Agent Collaboration for Automated Vulnerability Repair
Automated Vulnerability Repair (AVR) has emerged as a critical defense against software security flaws, aiming to triage
AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents
Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is eas
SynMark: Semantic-Coordinate Multi-Bit Watermarking during LLM Code Generation
LLM-generated code is increasingly reused across downstream applications and often undergoes identifier renaming or stru
SEMPRE: Semantic-Aware Protocol Reverse Engineering via Consistency-Driven Joint Optimization
Protocol reverse engineering (PRE) is essential for understanding undocumented or proprietary communication formats, ena
Ulysses: A Security Harness For Synthesizing Verifiable Web Exploits
How can an AI agent automatically discover security vulnerabilities in any software repository? Existing approaches use
Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure
In the post-API landscape, social-media profiling has become inexpensive and automated: Large Language Models (LLMs) can
AgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack
Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications
AfterDeleteBench: Auditing Post-Deletion Information Persistence in LLM Agents
Many LLM agents maintain external persistent memory and derive additional state from past interactions, such as summarie
Weaponizing the Exit: Input Privacy Leakage via Exit Routing Manipulation in Multi-Exit Networks
Multi-exit networks improve inference efficiency by allowing inputs to terminate early at intermediate exits. We identif
SecLog-Bench: A Scalable Benchmark for Cybersecurity Log Reasoning with Scaffolded Evidence
Large language models (LLMs) have shown strong potential for cybersecurity, leading to growing interest in LLM-based aut
Bridging Number-Theoretic Primality Testing And Algorithmic Optimization: An Adaptive Cryptographic Framework
The security of modern public-key cryptographic systems, such as RSA, Diffie-Hellman, and ECC, depends entirely on the c
Amplifying Latency and Cost of LLM Inference via Rowhammer Attack
Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time (JI
[原创]IDAPro v9.4.260714 汉化补丁修正错误
[原创]IDAPro v9.4.260714 汉化补丁修正错误
[原创]CVE-2020-6507利用链
CVE-2020-6507
[原创]CVE-2020-6507利用链