pgm-attack

PGM-attack Overview Official code for our paper, Poisoning Attacks on the PGM-index. Quick Start 1. Clone and submodules git clone REPOSITORY LINK cd pgm-index-poisoning git submodule update --init --recursive 2. Build ./scripts/build.sh Requires CMake see Dependencies. Outputs go under build/...

PURPOSE: Poisoning Conflict Resolution in RAG Via Proxy-Fact-Grounded Updates

In Retrieval-Augmented Generation RAG, post-retrieval conflict resolution arbitrates among noisy or contradictory retrieved passages. However, the robustness of this safeguard against knowledge poisoning has not been adequately studied. Existing black-box poisoning methods all assert the target...

EUVD-2026-47670

In NLnet Labs Unbound 1.6.0 up to and including 1.25.1, a replay of a wildcard rrset as another piece of data, could be briefly considered DNSSEC secure based only on the RRSIG validation and stored into cache, before later validation treats it as bogus based on NSEC validation. When the resolvin...

Securing Autonomous Vehicle Systems Via Twin-Aware Federated Reinforcement Learning

Federated reinforcement learning FRL is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby enhancing privacy and scalability in the decision-making process within dynamic vehicular environments. However, poisoning attacks pose a significant threat...

Deep-Research Agents Can Be Poisoned Via User-Generated Content

Deep-research agents, i.e., systems that rely on multi-agent pipelines to iteratively retrieve, synthesize, and cite Web content in order to produce structured reports, are rapidly replacing traditional search for both routine and complex information needs. These agents issue many related queries...

Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems

Cyber-Physical Systems CPS integrate sensing, communication, computation, and control to support critical infrastructure, including smart grids, industrial automation, and control systems. In the electrical utility domain, various controllers are used in CPS to ensure the system detects and...

Embedded Malicious Code

Overview Affected versions of this package are vulnerable to Embedded Malicious Code that conceals a credential stealer worm. A malicious actor managed to extract a GitHub Actions OIDC token from the runner process and publish tampered versions of 42 @tanstack/ packages to npm, which then spread ...

On the Dangers of Poisoned LLMs in Security Automation

This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited dataset, can introduce significant bias, to the extent tha...

CVE-2025-52647 HCL BigFix WebUI is affected by a host header poisoning vulnerability

The BigFix WebUI application responds with HOST information from the HTTP header field making it vulnerable to Host Header Poisoning Attacks...

EUVD-2011-0189

Malware in sbrugna...

EUVD-2020-9457

Malware in sbrugna...

EUVD-2024-0870

Malicious code in bioql PyPI...

FuncPoison: Poisoning Function Library to Hijack Multi-Agent Autonomous Driving Systems

Autonomous driving systems increasingly rely on multi-agent architectures powered by large language models LLMs, where specialized agents collaborate to perceive, reason, and plan. A key component of these systems is the shared function library, a collection of software tools that agents use to...

Ubuntu: Security Advisory (USN-7666-1)

The remote host is missing an update for the SPDX-FileCopyrightText: 2025 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

CVE-2025-40776

A named caching resolver that is configured to send ECS EDNS Client Subnet options may be vulnerable to a cache-poisoning attack. This issue affects BIND 9 versions 9.11.3-S1 through 9.16.50-S1, 9.18.11-S1 through 9.18.37-S1, and 9.20.9-S1 through 9.20.10-S1...

PT-2025-29825 · Isc · Bind

Name of the Vulnerable Software and Affected Versions: BIND 9 versions 9.11.3-S1 through 9.16.50-S1 BIND 9 versions 9.18.11-S1 through 9.18.37-S1 BIND 9 versions 9.20.9-S1 through 9.20.10-S1 Description: A named caching resolver configured to send ECS EDNS Client Subnet options may be vulnerable ...

@nx/azure-cache Vulnerable to Build Cache Poisoning via Untrusted Pull Requests

A critical security vulnerability exists in remote cache extensions for common build systems utilizing bucket-based remote cache such as those using Amazon S3, Google Cloud Storage, or similar object storage that allows any contributor with pull request privileges to inject compromised artifacts...

Poisoning Behavioral-Based Worker Selection in Mobile Crowdsensing Using Generative Adversarial Networks

With the widespread adoption of Artificial intelligence AI, AI-based tools and components are becoming omnipresent in today's solutions. However, these components and tools are posing a significant threat when it comes to adversarial attacks. Mobile Crowdsensing MCS is a sensing paradigm that...

BadReward: Clean-Label Poisoning of Reward Models in Text-To-Image RLHF

Reinforcement Learning from Human Feedback RLHF is crucial for aligning text-to-image T2I models with human preferences. However, RLHF's feedback mechanism also opens new pathways for adversaries. This paper demonstrates the feasibility of hijacking T2I models by poisoning a small fraction of...

Trojan Horse Hunt in Time Series Forecasting for Space Operations

This competition hosted on Kaggle https://www.kaggle.com/competitions/trojan-horse-hunt-in-space is the first part of a series of follow-up competitions and hackathons related to the "Assurance for Space Domain AI Applications" project funded by the European Space Agency...