Gadi Evron - Slashdot User

Submission + - RAPTOR: Autonomous Offensive/Defensive Research Framework based on Claude Code (github.com)

Submitted by Anonymous Coward on Tuesday December 02, 2025 @04:31AM

An anonymous reader writes: RAPTOR empowers security research with agentic workflows and automation. It combines traditional security tools with agentic automation and analysis, deeply understands your code, proves exploitability, and proposes patches.

First use: It generated patches for the FFmpeg Project Zero vulnerabilities.

Written by Gadi Evron, Daniel Cuthbert, Thomas Dullien (Halvar Flake), and Michael Bargury.

Submission + - Schneier and Raghavan: AI Agents Are Compromised by Design

Submitted by Gadi Evron on Monday October 13, 2025 @09:10PM

Gadi Evron writes: Bruce Schneier and Barath Raghavan say agentic AI is already broken at the core. In their IEEE Security & Privacy essay (https://www.computer.org/csdl/magazine/sp/5555/01/11194053/2aB2Rf5nZ0k), they argue that AI agents run on untrusted data, use unverified tools, and make decisions in hostile environments.

Every part of the OODA loop (observe, orient, decide, act) is open to attack. Prompt injection, data poisoning, and tool misuse corrupt the system from the inside. The model’s strength, treating all input as equal, also makes it exploitable.

They call this the AI security trilemma: fast, smart, or secure. Pick two. Integrity isn’t a feature you bolt on later. It has to be built in from the start.

Comment Re:reminds me of the old days (Score 1) 186

by Gadi Evron on Saturday May 08, 2004 @01:40PM (#9094382) Attached to: Breaking RSA Keys by Listening to Your Computer

Actually, that sounds more like TEMPEST. The magnetic interferance on the unshielded cable sounds exactly that, or am I wrong?

Slashdot Top Deals