Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-Cache in LLM Inference

The Key-Value KV cache, which stores intermediate attention computations Key and Value pairs to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model LLM inference. However, this efficiency optimization introduces significant yet underexplored privacy risk...

MADPromptS: Unlocking Zero-Shot Morphing Attack Detection with Multiple Prompt Aggregation

Face Morphing Attack Detection MAD is a critical challenge in face recognition security, where attackers can fool systems by interpolating the identity information of two or more individuals into a single face image, resulting in samples that can be verified as belonging to multiple identities by...

Physical Attacks Leading to Bypass of ASP Boot ROM Secure Boot

Summary Researchers shared a report titled “Code Execution on Zen 4 PSP using Voltage Fault Injection.” In the paper, the researchers reported their findings on Voltage Fault Injection VFI attacks targeting AMD “Zen 4” CPUs, specifically the Ryzen™ 8600G model. The researchers claim these types o...

IAG: Input-Aware Backdoor Attack on VLMs for Visual Grounding

Vision-language models VLMs have shown significant advancements in tasks such as visual grounding, where they localize specific objects in images based on natural language queries and images. However, security issues in visual grounding tasks for VLMs remain underexplored, especially in the conte...

Security Bulletin: NVIDIA Megatron LM - August 2025

NVIDIA has released a software update for NVIDIA® Megatron LM. To protect your system, clone or update this software to version 0.12.2 or later from Releases · NVIDIA/Megatron-LM on GitHub. Go to NVIDIA Product Security...

Linux Distros Unpatched Vulnerability : CVE-2025-21913

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: x86/amdnb: Use rdmsrsafe in amdgetmmconfigrange Xen doesn't offer MSRFAM10HMMIOCONFBASE to a...

CGA-728H-VF3G-82GW

Bulletin has no description...

CVE-2025-45146

ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/datamanager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data...

BIT-LIBPHP-2025-1219 libxml streams use wrong content-type header when requesting a redirected resource

In PHP from 8.1. before 8.1.32, from 8.2. before 8.2.28, from 8.3. before 8.3.19, from 8.4. before 8.4.5, when requesting a HTTP resource using the DOM or SimpleXML extensions, the wrong content-type header is used to determine the charset when the requested resource performs a redirect. This may...

Malicious code in securitycontext-model-paypal (npm)

--- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis d0f5dc5cd2ec64246a68ae3d6a8a63b03e25442841125c4fcaf8601002d97bb2 The OpenSSF Package Analysis project identified 'securitycontext-model-paypal' @ 2.2.22 npm as malicious. It is considered malicious because: -...

MAL-2025-6820 Malicious code in securitycontext-model-paypal (npm)

--- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis d0f5dc5cd2ec64246a68ae3d6a8a63b03e25442841125c4fcaf8601002d97bb2 The OpenSSF Package Analysis project identified 'securitycontext-model-paypal' @ 2.2.22 npm as malicious. It is considered malicious because: -...

Duplicate Advisory: Keras safe mode bypass vulnerability

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-c9rc-mg46-23w3. This link is maintained to preserve external references. Original Description A safe mode bypass vulnerability in the Model.loadmodel method in Keras versions 3.0.0 through 3.10.0 allows an...

GHSA-PWQ7-2GVJ-VG9V Duplicate Advisory: Keras safe mode bypass vulnerability

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-c9rc-mg46-23w3. This link is maintained to preserve external references. Original Description A safe mode bypass vulnerability in the Model.loadmodel method in Keras versions 3.0.0 through 3.10.0 allows an...

PYSEC-2025-75

A safe mode bypass vulnerability in the Model.loadmodel method in Keras versions 3.0.0 through 3.10.0 allows an attacker to achieve arbitrary code execution by convincing a user to load a specially crafted .keras model archive...

PYSEC-2025-75

A safe mode bypass vulnerability in the Model.loadmodel method in Keras versions 3.0.0 through 3.10.0 allows an attacker to achieve arbitrary code execution by convincing a user to load a specially crafted .keras model archive...

AZL-66171 CVE-2025-8747 affecting package keras for versions less than 3.3.3-3

A safe mode bypass vulnerability in the Model.loadmodel method in Keras versions 3.0.0 through 3.10.0 allows an attacker to achieve arbitrary code execution by convincing a user to load a specially crafted .keras model archive...

UBUNTU-CVE-2025-8747

A safe mode bypass vulnerability in the Model.loadmodel method in Keras versions 3.0.0 through 3.10.0 allows an attacker to achieve arbitrary code execution by convincing a user to load a specially crafted .keras model archive...

Deserialization of Untrusted Data

Overview keras is a Keras is a high-level neural networks API for Python.. Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the function savinglib.loadmodel, which identifies the model source file, directory, or Hugging Face repository and then calls the...

CGA-3X64-84VM-FW4J

Bulletin has no description...

CVE-2025-8747 Keras safe_mode bypass allows arbitrary code execution when loading a malicious model.

A safe mode bypass vulnerability in the Model.loadmodel method in Keras versions 3.0.0 through 3.10.0 allows an attacker to achieve arbitrary code execution by convincing a user to load a specially crafted .keras model archive...