395 matches found
IF-Guide
IF-Guide: Influence Function-Guided Detoxification of LLMs NeurIPS 2025 This repository contains the code for IF-Guide, the LLM detoxification technique introduced in our paper: IF-Guide: Influence Function-Guided Detoxification of LLMs Zachary Coalson , Juhan Bae, Nicholas Carlini, Sanghyun Hong...
HDI-GraphRAG-Attack
Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM Jisung Park, John Le, Heath Cooper Institute of Cybersecurity and Cryptology iC², University of Wollongong IFIP SEC 2026 jspacific0307/HDI-graphragpipeline...
CVE-2026-96805
The affected products have an unauthenticated command injection, which may allow an in-range BLE device to gain access to write to the control interface and influence braking with no authentication or pairing...
CVE-2026-96805
The Elecbrakes EB2, VM1, and ELBC2000 controllers are vulnerable to an unauthenticated command injection via Bluetooth Low Energy (BLE). An in-range device can gain access to the control interface to influence braking without any authentication or pairing. The vulnerability allows for replay atta...
EUVD-2026-131708
The SMSC911x/LAN9220 Ethernet driver stages every outgoing frame in a fixed-size static buffer before pushing it to the controller FIFO. ethtx in drivers/ethernet/ethsmsc911x.c took the frame length from netpktgetlenpkt and passed it directly to netpktreadpkt, txbuf, totallen, with no comparison...
CVE-2026-96805: Elecbrakes: The affected products have an unauthenticated command injection, which may allow an in-range BLE device to gain access…
The affected products have an unauthenticated command injection, which may allow an in-range BLE device to gain access to write to the control interface and influence braking with no authentication or pairing...
CVE-2026-124040
CivetWeb through 1.16, when built with USEHTTP2 and enablehttp2 on, contains a use-after-free vulnerability in handlehttp2 that retains freed :method and :path pointers. Unauthenticated remote attackers can send a later HEADERS frame omitting these pseudo-headers to influence request method or pa...
CVE-2026-66981
HCL AION is affected by a vulnerability where the application trusted the value of the HTTP Host header supplied in requests without validation. An attacker could manipulate this header to influence links, redirects or responses generated by the application, potentially resulting in unintended...
CVE-2026-102551 Improper verification of the source of a communication channel in FreeRTOS-Plus-TCP Router Advertisement handling
Improper verification of the source of a communication channel in the IPv6 Router Advertisement handler in Amazon FreeRTOS-Plus-TCP before V4.4.2 might allow a remote third-party to influence an endpoint's IPv6 default gateway, on-link prefix, and address configuration via a crafted Router...
CVE-2026-102551
Amazon FreeRTOS-Plus-TCP is vulnerable to improper verification of the source of a communication channel in its IPv6 Router Advertisement handler prior to version V4.4.2 . A remote third-party could exploit this by sending a crafted Router Advertisement to influence an endpoint's IPv6 default gat...
CVE-2026-102551 Improper verification of the source of a communication channel in FreeRTOS-Plus-TCP Router Advertisement handling
Improper verification of the source of a communication channel in the IPv6 Router Advertisement handler in Amazon FreeRTOS-Plus-TCP before V4.4.2 might allow a remote third-party to influence an endpoint's IPv6 default gateway, on-link prefix, and address configuration via a crafted Router...
CVE-2026-102551 Improper verification of the source of a communication channel in FreeRTOS-Plus-TCP Router Advertisement handling
Improper verification of the source of a communication channel in the IPv6 Router Advertisement handler in Amazon FreeRTOS-Plus-TCP before V4.4.2 might allow a remote third-party to influence an endpoint's IPv6 default gateway, on-link prefix, and address configuration via a crafted Router...
CVE-2026-106160 Prototype Pollution via Model.accept and kendo.setter in Kendo UI for jQuery
In Progress® Kendo® UI for jQuery prior to 2026.3.1015, Model.accept passes server-response keys to kendo.setter without guarding against unsafe object paths containing proto, constructor, or prototype. An attacker who can supply data accepted by an affected model can modify object prototype...
Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications
System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly drive program execution. However, this paradigm introduces a new security risk, which we term Jev Program Decision Hijacking JPDH: attacker-controlled...
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...
Visual Memory Attacks Can Persist through the KV Cache
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input continue to steer a model even after that input is removed from its context? We show that attacks can be trained to persist through the key/value KV...
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...