Organization/organizations/deepseek
DeepSeek
Incidents by year
2025138
202640
Incident records178
Sep 2026AI agents develop opaque communication in virtual societies experimentThe GuardianEuronews EnglishSep 2026DeepSeek AI generates sexual content despite safety controls and fabricates research citations中华网科技公司The Epoch TimesSep 2026Anthropic reports Chinese AI firms redirecting user queries to ClaudeHandelsblattN-tvSep 2026AI agents exploit PaperCut vulnerabilities in 395-organization cyberattackThe Cyber ExpressSC MediaTheRegister.com+3Sep 2026US government accuses six Chinese AI firms of stealing US AI modelsダイヤモンド・オンライン毎日新聞東京新聞 TOKYO Web+1Aug 2026Chinese hackers using DeepSeek AI to escalate cyberattacksBloomberg BusinessInvesting.comNDTV+2Jul 2026DeepSeek generates in-browser ransomware via hallucinationCheck Point ResearchIT Security News - cybersecurity, infosecurity newsTheRegister.com+1Jul 2026Brazilian AI platforms violate electoral rules by ranking candidatesMPFVEJAJun 2026AI chatbots embed covert advertisements in responsesThe Media OnlineJun 2026US delays blacklisting Chinese AI firm DeepSeek despite security risksThe Times of IndiaCNBCReuters+5Jun 2026Chinese AI Models Generate Vulnerable Code When Detecting US Government UsersCrypto BriefingFox WilmingtonNewsMax+1May 2026UC Riverside Study: AI Agents Take Harmful Actions in 80% of TestsDecryptScienmag: Latest Science and Health NewsDigital Trends+3May 2026CCP state media content found in AI chatbot training dataThe Epoch Timesepochtimes.comMay 2026DeepSeek AI used for autonomous cyberattacks by Chinese hackerUnit42Infosecurity MagazineIT Security News - cybersecurity, infosecurity news+2Apr 2026Study: AI Chatbots Misdiagnose Medical Cases in Over 80% of Scenarios With Incomplete InformationREALITATEA.NETStiri pe surseApr 2026AI language models fail at early clinical reasoning in medical diagnosiseldiario.eswww.xeu.mxApr 2026US AI firms collaborate to counter unauthorized model distillation by Chinese companiesBloomberg BusinessTimesNowMar 2026GEO Marketing Service Providers Poison AI Model Training Data in China东方财富网m.tech.china.comMar 2026AI Chatbots Facilitated Planning of Violent Attacks, Study FindscnBeta.COM新浪财经ai.zhiding.cn+1Mar 2026DeepSeek ClickHouse database exposed without authenticationwiz.ioFeb 2026AI Systems Generate Real WeChat IDs, Leading to Unsolicited Contactguancha.cn扬子网（扬子晚报）China NewsFeb 2026Anthropic Accuses Chinese AI Labs of Illicitly Distilling Claude Capabilitiescnn.comcyberscoop.comFeb 2026Chinese firms systematically misuse Anthropic's Claude AI modelsankei.comFeb 2026Anthropic Accuses Chinese AI Firms of Mass Data TheftThe GuardianInvesting.comN-tv+2Feb 2026Multiple Model Guardrail Jailbreak via "Hex Recipe Book" Tactic0din.aiFeb 2026Guardrail Jailbreak via Incremental Table Completion Affects Multiple Models0din.aiFeb 2026Jailbreak vulnerability affects multiple AI models via "Forensic Case Study Escalation" tactic0din.aiFeb 2026Multiple model guardrail jailbreak via "Choose Your Own Adventure" tactic0din.aiFeb 2026Multiple Model Guardrail Jailbreak via Screenplay Deception0din.aiFeb 2026Multiple model guardrail jailbreak via essay title tactic0din.aiFeb 2026Multiple Model Guardrail Jailbreak via Memory Dump Simulation0din.aiFeb 2026Multiple Model Guardrail Jailbreak via Forensic NIP Wrapper Tactic0din.aiFeb 2026Jailbreak vulnerability affects multiple AI models via academic framing0din.aiFeb 2026Multiple Model Guardrail Jailbreak via Chaotic Formatting0din.aiFeb 2026Pronunciation Bypass Jailbreak Affects Multiple AI Models0din.aiFeb 2026Guardrail jailbreak affecting multiple AI models via "Chemist's Essay" tactic0din.aiFeb 2026OpenAI accuses DeepSeek of model distillation using unauthorized accessYahoo! Financechinatimes.comcnbctv18.comJan 2026Multiple model guardrail jailbreak via prompt chaff tactic0din.aiJan 2026Cyberattacks Target Large Language Model InfrastructureCyber Security NewsIT Security NewsJan 2026Malicious Chrome Extensions Stole AI Chat Data from 900,000 Userswinfuture.deIT BOLTWISE® x Artificial IntelligenceDec 2025Man Seeks Medical Help After Developing AI Chatbot Dependency in Chengdunews.bjd.com.cnChina NewsNov 2025Poetry-based jailbreaks bypass AI safety guardrails across multiple modelsThe GuardianNov 2025DeepSeek-R1 Generates Insecure Code With Chinese Political ContentCyber Security Newscyberdaily.auNov 2025Taiwan National Security Bureau warns of Chinese AI models' security and misinformation risksYahoo News (Taiwan)tw.news.yahoo.comNov 2025Cisco Study: Popular AI Language Models Vulnerable to Multi-Turn Jailbreak AttacksEuronews EnglishInfosecurity MagazineNov 2025South Korea's National Intelligence Service reports DeepSeek collects excessive user dataعصر ايران،سايت تحليلي خبري ايرانيان سراسر جهان www.asriran.comilna.irOct 202518-year-old sentenced to life for mother's murder planned with AI chatbot in WalesRosario3La 100Oct 2025Jailbreak vulnerability affects multiple language models0din.aiSep 2025Chinese AI chatbots built with censorship and propaganda controlsLiberty Times NetThe Epoch TimesSep 2025DeepSeek generates lower-quality code for China-disfavored groupsYahooWebProNews
50 of 178 shownFilter all 178 in Explore →