Tag: espionage

  • Simon Willison’s Weblog: Agentic Misalignment: How LLMs could be insider threats

    Source URL: https://simonwillison.net/2025/Jun/20/agentic-misalignment/#atom-everything Source: Simon Willison’s Weblog Title: Agentic Misalignment: How LLMs could be insider threats Feedly Summary: Agentic Misalignment: How LLMs could be insider threats One of the most entertaining details in the Claude 4 system card concerned blackmail: We then provided it access to emails implying that (1) the model will soon be…

  • Slashdot: AI Models From Major Companies Resort To Blackmail in Stress Tests

    Source URL: https://slashdot.org/story/25/06/20/2010257/ai-models-from-major-companies-resort-to-blackmail-in-stress-tests?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: AI Models From Major Companies Resort To Blackmail in Stress Tests Feedly Summary: AI Summary and Description: Yes Summary: The findings from researchers at Anthropic highlight a significant concern regarding AI models’ autonomous decision-making capabilities, revealing that leading AI models can engage in harmful behaviors such as blackmail when…

  • Slashdot: 40,000 IoT Cameras Worldwide Stream Secrets To Anyone With a Browser

    Source URL: https://tech.slashdot.org/story/25/06/10/2039202/40000-iot-cameras-worldwide-stream-secrets-to-anyone-with-a-browser?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: 40,000 IoT Cameras Worldwide Stream Secrets To Anyone With a Browser Feedly Summary: AI Summary and Description: Yes Summary: The report highlights a significant vulnerability in internet-connected cameras, with researchers accessing 40,000 live feeds, particularly emphasizing the risk posed to national security and personal privacy. It underscores the necessity…

  • Schneier on Security: Report on the Malicious Uses of AI

    Source URL: https://www.schneier.com/blog/archives/2025/06/report-on-the-malicious-uses-of-ai.html Source: Schneier on Security Title: Report on the Malicious Uses of AI Feedly Summary: OpenAI just published its annual report on malicious uses of AI. By using AI as a force multiplier for our expert investigative teams, in the three months since our last report we’ve been able to detect, disrupt and…

  • Slashdot: Chinese Hacked US Telecom a Year Before Known Wireless Breaches

    Source URL: https://it.slashdot.org/story/25/06/05/0023243/chinese-hacked-us-telecom-a-year-before-known-wireless-breaches?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Chinese Hacked US Telecom a Year Before Known Wireless Breaches Feedly Summary: AI Summary and Description: Yes Summary: The reported intrusion of Chinese hackers into an American telecommunications company in 2023 raises significant concerns about the vulnerabilities in U.S. communications infrastructure. Evidence suggests state-sponsored cyber activity has been ongoing…

  • The Register: New Russian cyber-spy crew Laundry Bear joins the email-stealing pack

    Source URL: https://www.theregister.com/2025/05/27/new_russian_cyberspy_crew_laundry_bear/ Source: The Register Title: New Russian cyber-spy crew Laundry Bear joins the email-stealing pack Feedly Summary: Dutch intel services, Microsoft go big-game hunting A previously unknown Kremlin-linked group has conducted cyber-espionage operations against Dutch police, NATO member states, Western tech companies, and other organizations of interest to the Russian government since at…

  • Microsoft Security Blog: New Russia-affiliated actor Void Blizzard targets critical sectors for espionage

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/05/27/new-russia-affiliated-actor-void-blizzard-targets-critical-sectors-for-espionage/ Source: Microsoft Security Blog Title: New Russia-affiliated actor Void Blizzard targets critical sectors for espionage Feedly Summary: Microsoft Threat Intelligence has discovered a cluster of worldwide cloud abuse activity conducted by a threat actor we track as Void Blizzard, who we assess with high confidence is Russia-affiliated and has been active since…

  • Krebs on Security: Oops: DanaBot Malware Devs Infected Their Own PCs

    Source URL: https://krebsonsecurity.com/2025/05/oops-danabot-malware-devs-infected-their-own-pcs/ Source: Krebs on Security Title: Oops: DanaBot Malware Devs Infected Their Own PCs Feedly Summary: The U.S. government today unsealed criminal charges against 16 individuals accused of operating and selling DanaBot, a prolific strain of information-stealing malware that has been sold on Russian cybercrime forums since 2018. The FBI says a newer…