MAL-2025-6105 Malicious code in model-providers (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis 3bc812776fc9ca2678deabf678d9dae58067e353d0d7131e35d68fa452ff57f5 The OpenSSF Package Analysis project identified 'model-providers' @...

GPUHammer: New RowHammer Attack Variant Degrades AI Models on NVIDIA GPUs

NVIDIA is urging customers to enable System-level Error Correction Codes ECC as a defense against a variant of a RowHammer attack demonstrated against its graphics processing units GPUs. "Risk of successful exploitation from RowHammer attacks varies based on DRAM device, platform, design...

LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing

We introduce the framework of LLM-Stackelberg games, a class of sequential decision-making models that integrate large language models LLMs into strategic interactions between a leader and a follower. Departing from classical Stackelberg assumptions of complete information and rational agents, ou...

LLMalMorph: on the Feasibility of Generating Variant Malware Using Large-Language-Models

Large Language Models LLMs have transformed software development and automated code generation. Motivated by these advancements, this paper explores the feasibility of LLMs in modifying malware source code to generate variants. We introduce LLMalMorph, a semi-automated framework that leverages...

Securing Transformer-Based AI Execution Via Unified TEEs and Crypto-Protected Accelerators

Recent advances in Transformer models, e.g., large language models LLMs, have brought tremendous breakthroughs in various artificial intelligence AI tasks, leading to their wide applications in many security-critical domains. Due to their unprecedented scale and prohibitively high development cos...

SUSE CVE-2025-53630

llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the ggufinitfromfileimpl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579...

Security update for rust-keylime

This update for rust-keylime fixes the following issues: CVE-2024-12224: idna: Fixed improper validation in punycode bsc1243861 Update to version 0.2.7+70: builddeps: bump wiremock from 0.6.2 to 0.6.3 builddeps: bump uuid from 1.16.0 to 1.17.0 lib: Introduce AgentIdentity structure gitignore: Add...

usb: cdns3: Fix deadlock when using NCM gadget

...

iio: imu: st_lsm6dsx: fix possible lockup in st_lsm6dsx_read_tagged_fifo

...

USB: wdm: close race between wdm_open and wdm_wwan_port_stop

...

Entangled Threats: a Unified Kill Chain Model for Quantum Machine Learning Security

Quantum Machine Learning QML systems inherit vulnerabilities from classical machine learning while introducing new attack surfaces rooted in the physical and algorithmic layers of quantum computing. Despite a growing body of research on individual attack vectors - ranging from adversarial poisoni...

Cross-site Scripting (XSS)

Overview suitable-django-autocomplete is an A suitable Django autocomplete widget using web components Affected versions of this package are vulnerable to Cross-site Scripting XSS via the ModelAutocompleteView class due to insufficient output encoding in the autocomplete functionality. The...

Hybrid LLM-Enhanced Intrusion Detection for Zero-Day Threats in IoT Networks

This paper presents a novel approach to intrusion detection by integrating traditional signature-based methods with the contextual understanding capabilities of the GPT-2 Large Language Model LLM. As cyber threats become increasingly sophisticated, particularly in distributed, heterogeneous, and...

Defending against Prompt Injection with a Few DefensiveTokens

When large language model LLM systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker is able to override the initial user task with an arbitrary...

Beyond the Worst Case: Extending Differential Privacy Guarantees to Realistic Adversaries

Differential Privacy DP is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior information, more sophisticated attack goals, and complex...

Towards Privacy-Preserving and Personalized Smart Homes Via Tailored Small Language Models

Large Language Models LLMs have showcased remarkable generalizability in language comprehension and hold significant potential to revolutionize human-computer interaction in smart homes. Existing LLM-based smart home assistants typically transmit user commands, along with user profiles and home...

Agent Safety Alignment Via Reinforcement Learning

The emergence of autonomous Large Language Model LLM agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to both user-initiated threats e.g., adversarial prompts and...

BarkBeetle: Stealing Decision Tree Models with Fault Injection

Machine learning models, particularly decision trees DTs, are widely adopted across various domains due to their interpretability and efficiency. However, as ML models become increasingly integrated into privacy-sensitive applications, concerns about their confidentiality have grown, particularly...

VulnCheck KEV: CVE-2024-51977

An unauthenticated attacker who can access either the HTTP service TCP port 80, the HTTPS service TCP port 443, or the IPP service TCP port 631, can leak several pieces of sensitive information from a vulnerable device. The URI path /etc/mntinfo.csv can be accessed via a GET request and no...

Enter, Exit, Page Fault, Leak: Testing Isolation Boundaries for Microarchitectural Leaks

CPUs provide isolation mechanisms like virtualization and privilege levels to protect software. Yet these focus on architectural isolation while typically overlooking microarchitectural side channels, exemplified by Meltdown and Foreshadow. Software must therefore supplement architectural defense...