Hackers weaponize Shellter red teaming tool to spread infostealersSecurity Affairs·Jul 9, 08:43 UTC · Jul 9, 2025AI safety & security in the wild45
35 open-source security tools to power your red team, SOC, and cloud securityHelp Net Security·Jun 18, 00:00 UTC · Jun 18, 2025AI safety & security30
Meta Launches LlamaFirewall Framework to Stop AI Jailbreaks, Injections, and Insecure CodeThe Hacker News·Apr 30, 07:08 UTC · Apr 30, 2025AI safety & security30
New Reports Uncover Jailbreaks, Unsafe Code, and Data Theft Risks in Leading AI SystemsThe Hacker News·Apr 29, 16:18 UTC · Apr 29, 2025AI safety & security30
New hack uses prompt injection to corrupt Gemini’s longArs Technica · Security·Feb 11, 22:13 UTC · Feb 11, 2025AI safety & security30
When Pentest Tools Go Brutal: Red-Teaming Tool Being Abused by Malicious ActorsPalo Alto Unit 42·Jun 5, 20:22 UTC · Jun 5, 2024AI safety & security30
US, China meeting this week to talk AI safety, risksCyberScoop·May 13, 09:00 UTC · May 13, 2024AI safety & security in the wild45
Put guardrails around AI use to protect your org, but be open to changesHelp Net Security·Dec 4, 00:00 UTC · Dec 4, 2023AI safety & security30
Bitdefender Offensive Services incorporates penetration testing and red team simulated attacksHelp Net Security·Oct 25, 00:00 UTC · Oct 25, 2023AI safety & security30
"I Had a Dream" and Generative AI JailbreaksThe Hacker News·Oct 9, 11:06 UTC · Oct 9, 2023AI safety & security30
Hackers Abusing BRc4 Red Team Penetration Tool in Attacks to Evade DetectionThe Hacker News·Jul 7, 05:12 UTC · Jul 7, 2022AI safety & security130
Red-teaming by DHS 'quietly and slowly' uncovers agency vulnerabilitiesCyberScoop·Jun 13, 21:21 UTC · Jun 13, 2018AI safety & security in the wild45
Cyber Security: Red Team, Blue Team and Purple TeamSecurity Affairs·Oct 6, 19:26 UTC · Oct 6, 2017AI safety & security30