Hacker News
- LeftoverLocals: Listening to LLM responses through leaked GPU local memory https://blog.trailofbits.com/2024/01/16/leftoverlocals-listening-to-llm-responses-through-leaked-gpu-local-memory/ 39 comments
Linking pages
- Graphics card flaw enables data theft in AMD, Apple, and Qualcomm chips by exploiting GPU memory | Tom's Hardware https://www.tomshardware.com/tech-industry/cyber-security/graphics-card-flaw-enables-data-theft-in-amd-apple-and-qualcomm-chips-by-exploiting-gpu-memory 18 comments
- A Flaw in Millions of Apple, AMD, and Qualcomm GPUs Could Expose AI Data | WIRED https://www.wired.com/story/leftoverlocals-gpu-vulnerability-generative-ai/ 13 comments
- New Flaw in Apple, AMD, and Qualcomm GPUs Could Expose AI Data - Cyber Kendra https://www.cyberkendra.com/2024/01/LeftoverLocals-flaws-leak-ai-data-via-gpu.html 1 comment
- AMD, Apple, Qualcomm GPUs leak AI data in LeftoverLocals attacks https://www.bleepingcomputer.com/news/security/amd-apple-qualcomm-gpus-leak-ai-data-in-leftoverlocals-attacks/ 1 comment
- Major security flaw in Apple, AMD, and Qualcomm GPUs puts AI data at risk https://interestingengineering.com/science/major-security-flaw-puts-ai-data-at-risk 0 comments
- Week in Ethereum News January 20, 2024 – Week in Ethereum News https://weekinethereumnews.com/week-in-ethereum-news-january-20-2024 0 comments
Linked pages
- Qualcomm Works with Meta to Enable On-device AI Applications Using Llama 2 | Qualcomm https://www.qualcomm.com/news/releases/2023/07/qualcomm-works-with-meta-to-enable-on-device-ai-applications-usi 101 comments
- GPU.zip https://www.hertzbleed.com/gpu.zip/ 37 comments
- To safely deploy generative AI in health care, models must be open source https://www.nature.com/articles/d41586-023-03803-y 34 comments
- Crashes, Hangs and Crazy Images by Adding Zero | by Alastair Donaldson | Medium https://medium.com/@afd_icl/crashes-hangs-and-crazy-images-by-adding-zero-689d15ce922b#.drtfzl4bo 23 comments
- Cloud GPU Comparison https://cloud-gpus.com 1 comment
- GitHub - CNugteren/CLBlast: Tuned OpenCL BLAS https://github.com/CNugteren/CLBlast 0 comments
- Lamini & AMD: Paving the Road to GPU-Rich Enterprise LLMs https://www.lamini.ai/blog/lamini-amd-paving-the-road-to-gpu-rich-enterprise-llms 0 comments
- Assessing the security posture of a widely used vision model: YOLOv7 | Trail of Bits Blog https://blog.trailofbits.com/2023/11/15/assessing-the-security-posture-of-a-widely-used-vision-model-yolov7/ 0 comments
Related searches:
Search whole site: site:blog.trailofbits.com
Search title: LeftoverLocals: Listening to LLM responses through leaked GPU local memory | Trail of Bits Blog
See how to search.