Addressing the Low-Code Security Elephant in the Room Permalink
Archive
Major Security Breach From Business Users’ Low-Code Apps Could Come in 2023, Analysts Warn Permalink
New whitepaper outlines the taxonomy of failure modes in AI agents ◆ Microsoft Security Blog Permalink
Project Zero: From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code Permalink
Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach Permalink
Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies Permalink
How ChatGPT Remembers You: A Deep Dive into Its Memory and Chat History Features · Embrace The Red Permalink
A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility Permalink
Build a Knowledge Graph with MCP Memory and Amazon Neptune ◆ by David Bechberger ◆ Apr, 2025 ◆ Medium Permalink
GitHub - haizelabs/get-haized: A subset of jailbreaks automatically discovered by the Haize Labs haizing suite. Permalink
Surviving on a Diet of Poisoned Fruit: Reducing the National Security Risks of America’s Cyber Dependencies ◆ CNAS Permalink
AI Security Requires Enterprise-Grade AI Discovery with Complete Coverage and Deep Context - Noma Security Permalink
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms - Google DeepMind Permalink
Cyber Hard Problems: Focused Steps Toward a Resilient Digital Future ◆ The National Academies Press Permalink
Enhancing Security in AI Agents with FIDES: A Formal Model Leveraging Information-Flow Control Permalink
Google Online Security Blog: Mitigating prompt injection attacks with a layered defense strategy Permalink
How I used o3 to find CVE-2025-37899, a remote zeroday vulnerability in the Linux kernel’s SMB implementation – Sean Heelan’s Blog Permalink
How to Perform Clipboard Forensics: ActivitiesCache.db, Memory Forensics and Clipboard History Permalink
Invited Talk: Overlooked Foundations: Exploits as Experiments and Constructive Proofs in the Science-of-Security ◆ USENIX Permalink
Lloyd’s of London: Versicherung soll Schäden durch KI-Halluzinationen abdecken ◆ heise online Permalink
Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity - METR Permalink
NeurIPS Poster PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics Permalink
Ok signing off Replit for the day by @jasonlk(Jason ✨👾SaaStr.Ai✨ Lemkin) ◆ Twitter Thread Reader Permalink
Project Zero: Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models Permalink
Revolutionizing Red-Teaming: The Single-Turn Crescendo Attack (STCA) on Large Language Models Permalink
Securing the Model Context Protocol: Building a safer agentic future on Windows ◆ Windows Experience Blog Permalink
Security to Model: Securing Artificial Intelligence to Strengthen Cybersecurity – Committee on Homeland Security Permalink
Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models Permalink
AI-powered PromptLocker ransomware is just an NYU research project — the code worked as a typical ransomware, selecting targets, exfiltrating selected data and encrypting volumes ◆ Tom’s Hardware Permalink
Jumping the line: How MCP servers can attack you before you ever use them -The Trail of Bits Blog Permalink
Microsoft under fire: Senator demands FTC investigation into ‘arsonist selling firefighting services’ ◆ CSO Online Permalink
One Token to rule them all - obtaining Global Admin in every Entra ID tenant via Actor tokens - dirkjanm.io Permalink
ShadowLeak: A Zero-Click, Service-Side Attack Exfiltrating Sensitive Data Using ChatGPT’s Agent Permalink