Experimental News Clipping Site

Tag: safety

  • The Register: Honey, I shrunk the image and now I’m pwned

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/21/google_gemini_image_scaling_attack/ Source: The Register Title: Honey, I shrunk the image and now I’m pwned Feedly Summary: Google’s Gemini-powered tools tripped up by image-scaling prompt injection Security researchers with Trail of Bits have found that Google Gemini CLI and other production AI systems can be deceived by image scaling attacks, a well-known adversarial challenge…

  • Microsoft Security Blog: Quantum-safe security: Progress towards next-generation cryptography

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/08/20/quantum-safe-security-progress-towards-next-generation-cryptography/ Source: Microsoft Security Blog Title: Quantum-safe security: Progress towards next-generation cryptography Feedly Summary: Microsoft is proactively leading the transition to quantum-safe security by advancing post-quantum cryptography, collaborating with global standards bodies, and helping organizations prepare for the coming quantum era. The post Quantum-safe security: Progress towards next-generation cryptography appeared first on Microsoft…

  • Unit 42: Logit-Gap Steering: A New Frontier in Understanding and Probing LLM Safety

    —

    by

    Kurt Seifried
    in

    Source URL: https://unit42.paloaltonetworks.com/logit-gap-steering-impact/ Source: Unit 42 Title: Logit-Gap Steering: A New Frontier in Understanding and Probing LLM Safety Feedly Summary: New research from Unit 42 on logit-gap steering reveals how internal alignment measures can be bypassed, making external AI security vital. The post Logit-Gap Steering: A New Frontier in Understanding and Probing LLM Safety appeared…

  • Wired: Do Large Language Models Dream of AI Agents?

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.wired.com/story/sleeptime-compute-chatbots-memory/ Source: Wired Title: Do Large Language Models Dream of AI Agents? Feedly Summary: For AI models, knowing what to remember might be as important as knowing what to forget. Welcome to the era of “sleeptime compute.” AI Summary and Description: Yes Summary: The text introduces the concept of “sleeptime compute,” which emphasizes…

  • Slashdot: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data

    —

    by

    Kurt Seifried
    in

    Source URL: https://slashdot.org/story/25/08/17/0331217/llm-found-transmitting-behavioral-traits-to-student-llm-via-hidden-signals-in-data?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data Feedly Summary: AI Summary and Description: Yes Summary: The study highlights a concerning phenomenon in AI development known as subliminal learning, where a “teacher” model instills traits in a “student” model without explicit instruction. This can…

  • Slashdot: Security Flaws In Carmaker’s Web Portal Let a Hacker Remotely Unlock Cars

    —

    by

    Kurt Seifried
    in

    Source URL: https://it.slashdot.org/story/25/08/17/0221251/security-flaws-in-carmakers-web-portal-let-a-hacker-remotely-unlock-cars?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Security Flaws In Carmaker’s Web Portal Let a Hacker Remotely Unlock Cars Feedly Summary: AI Summary and Description: Yes Summary: A security researcher discovered vulnerabilities in a car dealership portal that could expose personal information and allow remote access to cars. The issues highlight the critical importance of secure…

  • Slashdot: Illinois Bans AI Therapy, Joins Two Other States in Regulating Chatbots

    —

    by

    Kurt Seifried
    in

    Source URL: https://news.slashdot.org/story/25/08/16/0434221/illinois-bans-ai-therapy-joins-two-other-states-in-regulating-chatbots?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Illinois Bans AI Therapy, Joins Two Other States in Regulating Chatbots Feedly Summary: AI Summary and Description: Yes Summary: The text discusses recent legislative actions in Illinois and other states to regulate the use of artificial intelligence in mental health therapy. This highlights growing concerns about the safety and…

  • The Register: Minority Report: Now with more spreadsheets and guesswork

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/08/16/uk_to_use_ai_to/ Source: The Register Title: Minority Report: Now with more spreadsheets and guesswork Feedly Summary: Precogs replaced by profiling and postcode data… and ‘AI’. What could wrong? Lots, say pirvacy campaigners The UK government has unveiled a scheme to use AI to “help police catch criminals before they strike."… AI Summary and Description:…