安全攻防 None 代理劫持攻击诱骗人工智能编码代理运行恶意代码 Cybersecurity researchers have described what they say is a new class of attack that can trick artificial intelligence ( attack can error 2026-06-12 info@thehackernews.com (The Hacker News)
智能AI None 代理人工智能控制评估中的攻击选择会显着降低安全性 06529v1 Announce Type: new Abstract: An attacker that strategically chooses when to attack is much harder to catch than attack safety and 2026-06-08 Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad IV, Joachim Schaeffer, Ram Potham, Tyler Tracy
智能AI None 语言模型中拒绝规避的潜在空间攻击 21706v1 Announce Type: new Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal the refusal and 2026-05-23 Giorgio Piras, Raffaele Mura, Fabio Brau, Maura Pintor, Luca Oneto, Fabio Roli, Battista Biggio
安全攻防 None Mini Shai-Hulud 通过受损的维护者帐户推送恶意 AntV npm 软件包 Cybersecurity researchers have discovered a fresh software supply chain attack campaign that has compromised various npm attack the npm 2026-05-19 info@thehackernews.com (The Hacker News)