IF-Guide

IF-Guide : Détoxification des LLM guidée par les fonctions d'influence NeurIPS 2025 Ce dépôt contient le code de IF-Guide, la technique de détoxification des LLM introduite dans notre article : IF-Guide : Détoxification des LLM guidée par les fonctions d'influence Zachary Coalson, Juhan Bae,...

CVE-2026-106559

The Backstage framework is vulnerable in the @backstage/plugin-scaffolder-backend-module-confluence-to-markdown package prior to version 0.3.25 . The root cause is improper input validation within the Confluence to Markdown scaffolder module. This flaw allows an attacker to influence file write o...

EUVD-2026-94372

Backstage is an open framework for building developer portals. Prior to 0.3.25, the @backstage/plugin-scaffolder-backend-module-confluence-to-markdown package is affected by improper input validation in confluence to markdown scaffolder module. Insufficient input validation in the Confluence to...

HDI-GraphRAG-Attack

Influence à décroissance par saut : Nouvelles vulnérabilités de l'indexation auxiliaire structurelle dans les pipelines GraphRAG avec LLM Jisung Park, John Le, Heath Cooper Institute of Cybersecurity and Cryptology iC², University of Wollongong IFIP SEC 2026 jspacific0307/HDI-graphragpipeline...

Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM

GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that determine how retrieval is prioritised at query time. Prior attacks target only instance-level components nodes, edges, triples, overlooking these...

MADBench: Benchmarking the Security of Multi-Agent Debate

Multi-agent debate MAD can improve large language model LLM reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the interactions that enable agents to correct mistakes can also spread adversarial errors and steer the agents toward an incorrect...

CVE-2026-93760

A flaw was found in Mongoid. This vulnerability allows a remote attacker, without requiring any credentials, to influence how the database evaluates queries by supplying malicious filter data. This can lead to the unintended disclosure of sensitive stored field values and may also result in reduc...

On Anthropic’s AI Misuse Report

Earlier this month, Anthropic published a long report detailing all of the Claude misuses it detected. Daniel Meissler usefully summarized the report into 117 findings. A few of the highlights: AI agents increasingly handled reconnaissance, exploitation, data theft, propaganda production,...

Astra Linux – Vulnerability in PostgresSQL 11

A vulnerability was discovered in PostgreSQL. This attack requires permission to create non-temporary objects in at least one schema, the ability to lure or wait for an administrator to create or update an affected extension in that schema, and the ability to lure or wait for a victim to use the...

Astra Linux – Vulnerability in Linux

A issue was discovered in the Linux kernel versions 2.6.39 through 5.10.16, as used in Xen. The block, net, and SCSI backends consider certain errors as ordinary bugs, which are deliberately designed to cause kernel crashes. For errors that may be influenced by guests such as memory exhaustion...

UBUNTU-CVE-2026-89554

In the Linux kernel, the following vulnerability has been resolved: mptcp: fix uninitialized localid in syncookie MPJOIN reconstruction mptcptokenjoincookieinitstate restores remotenonce, localnonce, backup, joinid, token and msk from the saved cookie entry when rebuilding the request socket for ...

CVE-2026-89554

CVE-2026-89554 affects the Linux kernel's MPTCP (Multipath TCP) implementation. When reconstructing a MP_JOIN request under SYN cookies, mptcp_token_join_cookie_init_state() fails to restore the local_id field from the saved cookie entry. Because the request-sock slab is SLAB_TYPESAFE_BY_RCU and ...

PYSEC-2026-3880 OpenHarness remote project-context commands allow persistent prompt poisoning

OpenHarness /issue and /prcomments slash commands lack remoteinvocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/prcomments....

OpenAI Bans Russian ChatGPT Accounts Used to Run Influence Operation

OpenAI on Tuesday said it banned a cluster of Russian ChatGPT accounts that used VPNs to bypass access restrictions and run an influence operation, which relied on its artificial intelligence AI tool to generate social media posts and comments that were shared on Substack, Telegram, X, Facebook a...

CVE-2026-15387: Acceptance of Extraneous Untrusted Data With Trusted Data

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have influenced the execution environment of Pipeline Execution Policy...

GitLab 19.1 < 19.1.7 / 19.2 < 19.2.5 / 19.3 < 19.3.1 (CVE-2026-15387)

The version of GitLab installed on the remote host is affected by a vulnerability, as follows: - GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with...

Social media platforms crack down on drone factory recruiting game

A video game about drone warfare may look like an unusual cybersecurity story. But cybersecurity isn't only about malware or stolen passwords. Sometimes it's about understanding how online platforms are used to influence decisions, build trust, and persuade people to share personal information or...

CVE-2026-71227

A flaw was found in libkcapi. A local attacker can influence an application that uses the Asynchronous Input/Output AIO interface. By reusing an AIO-enabled handle after a prior completion error, the kcapiaioreadall function can enter a non-terminating wait loop. This can lead to a persistent...

SUSE CVE-2026-40246

free5GC is an open-source implementation of the 5G core network. In versions 1.4.2 and below of the UDR service, the handler for deleting Traffic Influence Subscriptions checks whether the influenceId path segment equals subs-to-notify, but does not return after sending the HTTP 404 response when...

SUSE CVE-2026-40247

free5GC is an open-source implementation of the 5G core network. In versions 4.2.1 and below of the UDR service, the handler for reading Traffic Influence Subscriptions checks whether the influenceId path segment equals subs-to-notify, but does not return after sending the HTTP 404 response when...