/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

Researchers describe a GPU vulnerability that allows attackers to exfiltrate data from local memory on some devices with Apple, Qualcomm, AMD, and other chips

Patching every device affected by the LeftoverLocals vulnerability—which includes some iPhones, iPads, and Macs—may prove difficult.

Wired

Context & Ripple Effects

LeftoverLocals extends a long-running class of hardware isolation failures: Meltdown and Spectre showed data could cross application boundaries through chip behavior, while later research continued to identify side-channel risks across major processor families.

The GPU focus matters because the affected set spans Apple, Qualcomm, AMD, and other chips, and because related coverage has also shown GPU image-compression behavior can expose cross-origin pixels. The central operational constraint here is that patching affected devices may be uneven or difficult.

First-order effects

  • Affected device and chip vendors must assess whether their GPU implementations can expose local memory and determine which software or firmware mitigations are available.
  • Owners of some iPhones, iPads, Macs, and other impacted devices face a potentially inconsistent remediation path rather than a single universal fix.

Second-order effects

  • Difficult patch coverage raises the value of mitigations in GPU drivers, operating systems, and applications, shifting more of the near-term response from silicon design to the software stack.
  • Vendors competing on GPU performance and broad device deployment will face added pressure to demonstrate memory isolation and to communicate which generations remain exposed.

Third-order effects

  • If GPU-local-memory flaws continue to recur, hardware security assurance will increasingly need to cover accelerators alongside CPUs, not treat GPUs as peripheral compute components.
  • The pattern could favor designs and platform policies that make isolation failures easier to contain or update, though the extent depends on whether vendors can deliver effective mitigations for deployed hardware.

The trend: LeftoverLocals is one data point in the widening security perimeter of heterogeneous computing, where GPU and accelerator memory isolation is becoming as consequential as CPU-side protection.

Discussion

  • @cachiporra.bsky.social Mr. Mooch on bluesky
    it feels like the entire computation industry has been having a leaded paint, leaded gasoline, arsenic, or black mold moment every month for the last decade [embedded post]
  • @jvquantum JV Quantum on x
    Uh oh! A flaw in millions of Apple AMD and Qualcomm GPUs might expose AI data. Patching up the LeftoverLocals vulnerability in affected devices, including iPhones, iPads, and Macs, could be quite the challenge. Time for some serious digital housekeeping,... https://www.wired.com/…
  • @heidykhlaaf Dr Heidy Khlaaf on x
    We're finally revealing a significant co-resident GPU vulnerability impacting AMD, Apple, Qualcomm, and Imagination GPUs that allows an attacker to listen into another user's LLM (e.g., llama.cpp) session across process and container boundaries!
  • @trailofbits @trailofbits on x
    LeftoverLocals impacts the security posture of GPU applications, especially LLMs and ML models that run on impacted GPU platforms. It highlights that many parts of the ML development stack, specifically GPUs, have unknown security risks. Read more: http://www.leftoverlocals.com/ …
  • @dguido Dan Guido on x
    In pursuit of speed, many GPU frameworks do not clear GPU local memory after running a kernel. Attackers can recover LLM Q&A by running a kernel on the same GPU. https://twitter.com/...
  • @trailofbits @trailofbits on x
    Our PoC can listen to another user's llama.cpp session across process or container boundaries. LeftoverLocals can leak ~5.5 MB per GPU invocation on an AMD Radeon RX 7900 XT running a 7B model on llama.cpp, adding up to ~181 MB for each LLM query. https://www.youtube.com/... [vid…
  • @heidykhlaaf Dr Heidy Khlaaf on x
    This vulnerability was found by the talented @Tyler_UCSC and highlights the unknown security posture of the ML stack (i.e., GPUs) and the increased attack surfaces faced when deploying LLMs and ML models. Read the feature from Wired here: https://www.wired.com/...
  • @lilyhnewman Lily Hay Newman on x
    GPU local memory security anxiety let's go (with @mattburgess1) https://www.wired.com/...
  • @jeff_weishaupt Jeff Weishaupt on x
    Thinking about using “local LLMs” as a way to protect sensitive data? Hold that thought... “we were able to build a PoC where an attacker can listen into another user's interactive LLM session (e.g., llama.cpp) across process or container boundaries” https://blog.trailofbits.com/…
  • @trailofbits @trailofbits on x
    Today, we are disclosing LeftoverLocals, a vulnerability that allows listening to LLM responses through leaked GPU local memory created by another process on Apple, Qualcomm, AMD, and Imagination GPUs (CVE-2023-4969) https://blog.trailofbits.com/ ... [image]
  • @backchnnl @backchnnl on x
    Patching every device affected by the LeftoverLocals vulnerability—which includes some iPhones, iPads, and Macs—may prove difficult. https://www.wired.com/...
  • @dguido Dan Guido on x
    We surveyed the main GPUs available today, but there's a rush of new startups vying for marketshare. How are we assessing the safety of new developments? [image]
  • @tyler_ucsc Tyler Sorensen on x
    It was really fun doing this work over the summer at ToB! A huge thanks for all of their support and everyone who engaged with us over the last few months. It's an exciting time for GPUs, and I hope that security and privacy can start to be a bigger focus!