Alaid TechThread 1 октября пройдет VK Security Confab. В продолжение доклада с OffZone про атакующих агентов в гостях у VK инженер из нашей команды Руслан углубится в анализ API-контрактов средствами AI-агентов. Успехи, факапы и полученный опыт — будем рады со всеми поделиться.…

OAS Presentation (Public).pdf9.2 MB

Презентация Руслана
#ProSecA

🔥 9
👍 1

Post #1449 456 Oct 3, 2025, 07:38 UTC

What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs

https://arxiv.org/pdf/2509.22796

Post #1448 588 Sep 30, 2025, 15:05 UTC

AI-powered workflow automation and AI Agents for AppSec, Fuzzing & Offensive Security

https://github.com/FuzzingLabs/fuzzforge_ai

👍 2

Post #1447 439 Sep 28, 2025, 12:47 UTC

Automated Patch Diff Analysis using LLMs

https://blog.syss.com/posts/automated-patch-diff-analysis-using-llms/

https://github.com/SySS-Research/diffalayze

SySS Tech Blog Automated Patch Diff Analysis using LLMs Large Language Models (LLMs) are increasingly integrated into AI workflows and agents to streamline a wide range of tasks. In this blog post, we introduce an approach for using LLMs for automated patch diff analysis. TL;DR Patch diffing is great for finding…

Post #1446 502 Sep 23, 2025, 05:40 UTC

EXPLORING GRAPHENEOS SECURE ALLOCATOR: HARDENED MALLOC

https://www.synacktiv.com/en/publications/exploring-grapheneos-secure-allocator-hardened-malloc

Synacktiv Exploring GrapheneOS secure allocator: Hardened Malloc

Post #1445 521 Sep 20, 2025, 05:03 UTC

ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System

https://team-atlanta.github.io/papers/TR-Team-Atlanta.pdf

👍 1
🔥 1

Post #1444 428 Sep 20, 2025, 04:25 UTC

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing

https://arxiv.org/pdf/2509.09207

Post #1443 467 Sep 18, 2025, 15:01 UTC

1 октября пройдет VK Security Confab. В продолжение доклада с OffZone про атакующих агентов в гостях у VK инженер из нашей команды Руслан углубится в анализ API-контрактов средствами AI-агентов. Успехи, факапы и полученный опыт — будем рады со всеми поделиться. Подробности тут

P.S. Появились видео докладов с OffZone.

Bug Bounty Edition Обсудим секреты и подводные камни Bug Bounty, техники поиска, ИИ, инструменты и найденные уязвимости.

👍 2

Post #1442 427 Sep 18, 2025, 07:04 UTC

securing ai agents.pdf.pdf7.3 MB

How to securely deploy agents that make sensitive decisions autonomously

Post #1441 410 Sep 18, 2025, 05:31 UTC

Alaid TechThread Завершился финальный этап DARPA AIxCC https://www.darpa.mil/news/2025/aixcc-results Участники начали делиться наработками: Первое место Team Atlanta https://team-atlanta.github.io Второе место Trail of Bits: https://www.trailofbits.com/buttercup/ https…

The Art of Vibe-Crashing
Seed generation in the LLM era

https://support.shellphish.net/blog/2025/09/02/shellphish-x-aixcc-dg/

support.shellphish.net The Art of Vibe-Crashing | Shellphish Support Syndicate The goal of Shellphish Support Syndicate is to support the Shellphish team in all their endeavors.

🔥 3

Post #1439 517 Sep 14, 2025, 10:25 UTC

All You Need Is A Fuzzing Brain: An LLM-Powered System for
Automated Vulnerability Detection and Patching

https://arxiv.org/pdf/2509.07225

👍 3

Post #1438 509 Sep 12, 2025, 20:50 UTC

Can AI weaponize new CVEs in under 15 minutes?

https://valmarelox.substack.com/p/can-ai-weaponize-new-cves-in-under

Substack Can AI weaponize new CVEs in under 15 minutes? If AI can mass-produce exploits, how much time do defenders really have left?

👍 2

Post #1437 516 Sep 7, 2025, 05:40 UTC

VULSOLVER : Vulnerability Detection via LLM-Driven Constraint Solving

https://arxiv.org/pdf/2509.00882

🔥 2

Post #1436 876 Sep 4, 2025, 14:47 UTC

Prompt. Scan. Exploit - Ai's Journey Through Zero-Days And A Thousand Bugs

https://youtu.be/y_aQQmDMaY4

YouTube Prompt. Scan. Exploit - Ai's Journey Through Zero-Days And A Thousand Bugs Joel Noguera (@niemand_sec) and Diego Jurado's (@djurado9) Talk as part of the Bug Bounty Village at DEF CON 33. Due to technical issues in the creator stages during the first day of DEF CON 33, they couldn't present their talk, so we are exclusively uploading…

🔥 1

Post #1435 414 Sep 3, 2025, 19:03 UTC

Slice: SAST + LLM Interprocedural Context Extractor

Built with: CodeQL, Tree-Sitter, OpenAI API

https://github.com/noperator/slice

GitHub GitHub - noperator/slice: SAST + LLM Interprocedural Context Extractor SAST + LLM Interprocedural Context Extractor. Contribute to noperator/slice development by creating an account on GitHub.

🔥 2

Post #1434 395 Sep 2, 2025, 18:21 UTC

Finding vulnerabilities in modern web apps using Claude Code and OpenAI Codex

https://semgrep.dev/blog/2025/finding-vulnerabilities-in-modern-web-apps-using-claude-code-and-openai-codex/

Semgrep Finding vulnerabilities in modern web apps using Claude Code and OpenAI Codex Our deep dive into AI Coding Agents capabilities for finding security vulnerabilities reveals surprising strengths, critical weaknesses, and a serious problem with consistency.

🔥 2

Older posts →