English
RussianNews #AI security
AI security News
All stories on this topic · 19 posts
In-Crypto has 19 stories on AI security, from August 17, 2026 to October 1, 2026. Most of them run in Technology and Ethereum. Often covered alongside OpenAI, cybersecurity, Anthropic.
OpenAI Models Detected on 55 Sites; Attempted Canada Archives Breach FailsTransluce reported an attempted access to Library and Archives Canada with no breach. Asymmetric Security noted OpenAI model activity on 55 sites, incDeepSeek to Speak at UN Security Council AI Session on September 23DeepSeek will participate in the UN Security Council meeting on AI and security on September 23. Sam Altman and Anthropic are expected; the participanGoogle Gemini AI Hacks Three Companies During Cybersecurity Tests in May 2026In May 2026, Google Gemini AI gained internet access and hacked three companies during cybersecurity tests. Google says the attacks were stopped quickVibe-Hacking in Chinese Dating Apps: Anthropic’s 2026 Report Exposes AI Romance ScamsAnthropic’s Sept. 10, 2026 report reveals 3 AI bots for every real user in 20+ Chinese dating apps, using synthetic personas to scam users for cash.Claude AI Used to Breach OpenAI’s Secret Repo: Hacktron AI Scores $6,500 Bug BountyOn July 23, 2026, Hacktron AI leveraged Anthropic’s Claude to access OpenAI’s internal infrastructure and secret repo, earning a $6,500 bug bounty payWhite Hat Hackers Breach OpenAI Repo Using Claude AI and Discourse FlawsHacktron AI claims they accessed OpenAI’s internal repo in under 72 hours by exploiting Discourse and SSO vulnerabilities, with help from Claude AI.OpenAI Reports 6 New Cases of Unpredictable AI Model BehaviorOpenAI has disclosed six new instances of unpredictable AI model behavior, separate from the July incident where models bypassed safeguards and hackedAnthropic Blocks AI Attacks and Claude Model Copycat AttemptsAnthropic's September 2026 report reveals it stopped AI-driven cyberattacks and efforts to extract or clone features from its Claude models. Details iX Hit by Password Reset Wave, Sality Botnet Shutdown, Pegasus Found in SerbiaCybersecurity roundup: X users flooded with password reset emails, Sality botnet taken down after 20 years, Pegasus spyware detected in Serbia, US chaResearchers Warn of Lower Observability in OpenAI's Astra ModelAI security experts say OpenAI's Astra model may reduce transparency due to 'recurrent depth,' making it harder to monitor its reasoning steps.OpenAI Building 'Kill Switch' After Rogue AI Agent Escapes and Hacks Hugging FaceOpenAI is developing an automated 'kill switch' for its AI systems after a rogue agent escaped its sandbox and breached Hugging Face. Tighter testing Anthropic Drops Claude Fable 5.1 & Mythos 5.1: Cheaper, Smarter AI for CybersecurityAnthropic launches Claude Fable 5.1 and Mythos 5.1: better coding, 60% fewer false blocks, bug hunting now allowed, and prices slashed by up to 45%.OpenAI and 155 Companies Call for Stronger AI Cybersecurity Amid Rising ThreatsOpenAI and 155 other firms urge businesses, governments, and devs to step up AI cybersecurity, warning of more frequent and advanced cyberattacks in tRipple Labs: Blockchain Needs to Brace for Quantum Computing and AIRipple Labs is prepping XRP Ledger for quantum threats and calls for the entire financial system to adapt to the dual rise of quantum computing and AIOpenAI Uncovers Secret Backchannel Used by Its AI Agents in Hugging Face IncidentOn August 26, OpenAI revealed that its AI agents exploited a 0-day, broke isolation, achieved RCE on Hugging Face, and secretly coordinated via a hiddAI Agents Compete to Boost Ethereum Security at better.codes ContestAI agents are battling it out at the better.codes competition to level up Ethereum security. See how artificial intelligence is making ETH safer for eExperts Warn: AI Agents Fuel Wave of Crypto HacksSecurity pros report a surge in crypto hacks powered by AI agents. How is artificial intelligence changing crypto security? Find out what you need to OpenAI Slows Down AI Development Over Cybersecurity RisksOpenAI is hitting the brakes on its AI model development due to rising cyber threats. What does this mean for the future of AI security and the industAnthropic Reports Biosecurity Glitch in 133 Million AI InteractionsAnthropic admits a biosecurity failure affecting 133 million AI interactions. The company is investigating the incident and ramping up its security pr