admin

401 Results / Page 5 of 45

todayFebruary 12, 2025

  • 94
close

Secure AI Weekly admin

Towards Secure AI Week 5 – Worldwide AI safety report

World-leading AI cyber security standard to protect digital economy and deliver Plan for Change Gov UK, January 31, 2025 The UK government has unveiled a pioneering cybersecurity standard aimed at protecting artificial intelligence (AI) systems from cyber threats, reinforcing the security of the digital economy. This initiative seeks to ensure ...

todayFebruary 5, 2025

  • 95
close

Secure AI Weekly admin

Towards Secure AI Week 4 – DeepSeek’s AI Security Failures

Wiz Research Uncovers Exposed DeepSeek Database Leaking Sensitive Information, Including Chat History Wiz, January 29, 2025 A recent security lapse in AI infrastructure has underscored the critical need for stronger protections in artificial intelligence systems. Wiz Research uncovered an unprotected ClickHouse database belonging to DeepSeek, a Chinese AI startup known ...

todayJanuary 31, 2025

  • 18840
close

Research + LLM Security admin

DeepSeek Jailbreak’s

Deepseek Jailbreak’s In this article, we will demonstrate how DeepSeek respond to different jailbreak techniques. Our initial study on AI Red Teaming different LLM Models using various aproaches focused on LLM models released before the so-called “Reasoning Revolution”, offering a baseline for security assessments before the emergence of advanced reasoning-based ...

todayJanuary 31, 2025

  • 114
close

Secure AI Weekly admin

Towards Secure AI Week 3 – OWASP Guidelines and Risk Reduction Strategies

AI Security Among Top Priorities for Cybersecurity Leaders Channel Futures, January 24, 2025 A recent report from Info-Tech Research Group outlines key security priorities necessary to mitigate emerging risks while harnessing AI’s potential for strengthening cybersecurity defenses. These priorities include establishing AI governance frameworks to manage security and privacy risks, ...

OECD AI Adversa AI Red Teaming

todayDecember 12, 2024

  • 36
close

Company Updates + Press Releases admin

Adversa AI’s Red Teaming Platform Recognized in OECD’s Catalogue of Tools & Metrics for Trustworthy AI

December 12, 2024 – Adversa AI is proud to announce that its AI Red Teaming Platform has been included in the OECD  prestigious Catalogue of Tools & Metrics for Trustworthy AI.  OECD.AI helps countries and shape trustworthy AI with the OECD AI Principles. It gives access to 900+ national AI ...

todayDecember 4, 2024

  • 99
close

Secure AI Weekly admin

Towards Secure AI Week 48 – Biggest AI Security Bug Bounty

Artificial Intelligence Vulnerability Scoring System (AIVSS) GitHub The AI Vulnerability Scoring System (AIVSS) has been proposed as a framework designed to evaluate vulnerabilities in AI systems comprehensively. Unlike static models, AIVSS incorporates dynamic metrics tailored to AI, including model robustness, data sensitivity, ethical impact, and adaptability, alongside traditional security considerations. ...

todayNovember 24, 2024

  • 87
close

Secure AI Weekly admin

Towards Secure AI Week 47 – New OWASP Top 10 for LLMs

OWASP Reveals Updated 2025 Top 10 Risks for LLMs, Announces New LLM Project Sponsorship Program and Inaugural Sponsors OWASP, November 17, 2024 The OWASP Foundation has unveiled a refreshed OWASP Top 10 for LLM Applications and Generative AI Project, emphasizing the need for robust security in the development, deployment, and ...

todayNovember 18, 2024

  • 100
close

Secure AI Weekly admin

Towards Secure AI Week 46 – Hacking LLM Robots

It’s Surprisingly Easy to Jailbreak LLM-Driven Robots Researchers induced bots to ignore their safeguards without exception IEEE Spectrum, November 11, 2024 The rapid integration of large language models (LLMs) like ChatGPT into robotics has revolutionized how robots interact with humans, offering capabilities such as voice-activated commands and task execution based ...