Backdooring Acoustic Foundation Models for Physically Realizable Triggers

Acoustic foundation models AFMs have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speaker verification with minimal resources. However, the security of applications based on AFMs remains largely underexplored. Our work addresses this ga...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2026-9856 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2026-9856 Source advisory:...

Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection

Face recognition systems are increasingly deployed in security-critical applications, yet they remain vulnerable to presentation and morph attacks. Presentation attack detection PAD and morphing attack detection MAD are therefore essential components of trustworthy face biometrics. Despite...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2026-9856 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2026-9856 Source advisory:...

Malicious code in @cloudplatform-single-spa/ml-foundation-models (npm)

Part of a dependency confusion attack campaign targeting the @cloudplatform-single-spa and @mlspace npm scopes. The attacker npm user mr.4nd3r50n published 139 scoped packages at the inflated version 99.99.99, which resolves ahead of any private registry version via npm's default version...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2026-5241 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2026-5241 Source advisory:...

Towards Intrusion Detection Systems for RPL-Based IoT Networks Using Foundation Models

AI-based intrusion detection systems IDS have shown promise in detecting attacks on IoT systems. In this work, we explore the use of foundation models to detect and identify attacks, with a specific focus on RPL-based IoT networks. We study multiple attack types, attack variations, and network...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2026-4372 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2026-4372 Source advisory:...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2026-4372 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2026-4372 Source advisory:...

Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents

Side-channel attacks exploit unintended information leakage from system behavior and continue to pose serious privacy risks in modern platforms. Despite extensive prior work, side-channel analysis remains largely manual and fragmented, typically assuming predefined target events and a fixed set o...

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single, predefined objectives, tightly coupling each attack to a...

Exploiting LLM Agent Supply Chains Via Payload-Less Skills

Autonomous agents powered by Large Language Models LLMs acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms a...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2026-1839 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2026-1839 Source advisory:...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2026-1839 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2026-1839 Source advisory:...

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the securit...

Okara: Detection and Attribution of TLS Man-In-The-Middle Vulnerabilities in Android Apps with Foundation Models

Transport Layer Security TLS is fundamental to secure online communication, yet vulnerabilities in certificate validation that enable Man-in-the-Middle MitM attacks remain a pervasive threat in Android apps. Existing detection tools are hampered by low-coverage UI interaction, costly...

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

Machine learning ML underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box attacks that exploit model comparisons. Larger models can be mor...

aiu-fms-testing-utils (0.0.2a3), pathology-foundation-models (>=0.0.2, <=0.0.4) +1 more potentially affected by CVE-2025-14929 via transformers (4.54.0)

transformers PYPI version 4.54.0 is affected by a known vulnerability. The following packages have a transitive dependency on transformers and may be impacted: - aiu-fms-testing-utils 0.0.2a3 - pathology-foundation-models =0.0.2, =0.1.0, =0.1.1 Source cves: CVE-2025-14929 Source advisory:...

Data Poisoning Vulnerabilities across Healthcare AI Architectures: A Security Threat Analysis

Healthcare AI systems face major vulnerabilities to data poisoning that current defenses and regulations cannot adequately address. We analyzed eight attack scenarios in four categories: architectural attacks on convolutional neural networks, large language models, and reinforcement learning...

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning DL models, including recent foundation models like large language models LLMs. Users can access different compressed model versions according to their resources and budget. However, while existi...