Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models

Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models LLMs and improve the overall trust in artificial intelligence AI systems. The tech giant's AI Security team said the scanner leverages three observable signals that ca...

Detecting backdoored language models at scale

Today, we are releasing new research on detecting backdoors in open-weight language models. Our research highlights several key properties of language model backdoors, laying the groundwork for a practical scanner designed to detect backdoored models at scale and improve overall trust in AI...

Detecting backdoored language models at scale

Today, we are releasing new research on detecting backdoors in open-weight language models. Our research highlights several key properties of language model backdoors, laying the groundwork for a practical scanner designed to detect backdoored models at scale and improve overall trust in AI...

Inference-Time Backdoors Via Hidden Instructions in LLM Chat Templates

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat in this context is backdoor attacks, in which adversaries embed hidden behaviors in language models that activate under specific conditions. Previous work has assumed th...

DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers

The widespread adoption of Vision Transformers ViTs elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors into released checkpoints. Existing ViT backdoor attacks largely rely on poisoned-data training, while prior data-free attempts typically require...

Sockpuppetting: Jailbreaking LLMs without Optimization through Output Prefix Injection

As open-weight large language models LLMs increase in capabilities, safeguarding them against malicious prompts and understanding possible attack vectors becomes ever more important. While automated jailbreaking methods like GCG Zou et al., 2023 remain effective, they often require substantial...

GHSA-XFHX-R7WW-5995 Duplicate Advisory: Google Keras Allocates Resources Without Limits or Throttling in the HDF5 weight loading component

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mgx6-5cf9-rr43. This link is maintained to preserve external references. Original Description Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 throu...

Duplicate Advisory: Google Keras Allocates Resources Without Limits or Throttling in the HDF5 weight loading component

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mgx6-5cf9-rr43. This link is maintained to preserve external references. Original Description Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 throu...

PYSEC-2026-73

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading componentin GoogleKeras3.0.0 through 3.13.0on all platformsallows a remote attackerto cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpretervia a crafted .keras archive containin...

CVE-2026-0897

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 through 3.13.0 on all platforms allows a remote attacker to cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpreter via a crafted .keras archive...

AZL-74631 CVE-2026-0897 affecting package keras for versions less than 3.3.3-6

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 through 3.13.0 on all platforms allows a remote attacker to cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpreter via a crafted .keras archive...

PYSEC-2026-73

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 through 3.13.0 on all platforms allows a remote attacker to cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpreter via a crafted .keras archive...

CVE-2026-0897 Denial of Service in Keras via Excessive Memory Allocation in HDF5 Metadata

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 through 3.13.0 on all platforms allows a remote attacker to cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpreter via a crafted .keras archive...

CVE-2026-0897

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 through 3.13.0 on all platforms allows a remote attacker to cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpreter via a crafted .keras archive...

Keras security vulnerabilities

Keras is an open-source deep learning framework with multiple backends. Versions 3.0.0 to 3.13.0 of Keras contain security vulnerabilities. These vulnerabilities stem from the HDF5 weight loading component, which allows unlimited or throttled resource allocation. This could allow remote attackers...

SUSE CVE-2023-54271

In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: Fix NULL deref caused by blkgpolicydata being installed before init blk-iocost sometimes causes the following crash: BUG: kernel NULL pointer dereference, address: 00000000000000e0 ... RIP: 0010:rawspinlock+0x17/0x30...

CVE-2023-54271

In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: Fix NULL deref caused by blkgpolicydata being installed before init blk-iocost sometimes causes the following crash: BUG: kernel NULL pointer dereference, address: 00000000000000e0 ... RIP: 0010:rawspinlock+0x17/0x30...

UBUNTU-CVE-2023-54271

In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: Fix NULL deref caused by blkgpolicydata being installed before init blk-iocost sometimes causes the following crash: BUG: kernel NULL pointer dereference, address: 00000000000000e0 ... RIP: 0010:rawspinlock+0x17/0x30...

CVE-2023-54271

CVE-2023-54271 concerns a NULL pointer dereference in the Linux kernel related to block cgroup handling. The issue arises when blkcg_activate_policy installs blkg_policy_data before ioc_weight policy data is fully initialized, causing a race with ioc_weight_write() that can encounter an uninitial...

CVE-2023-54271 blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init

In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: Fix NULL deref caused by blkgpolicydata being installed before init blk-iocost sometimes causes the following crash: BUG: kernel NULL pointer dereference, address: 00000000000000e0 ... RIP: 0010:rawspinlock+0x17/0x30...