30384 matches found
PT-2026-102628
ClipBucket v5 through 5.5.3-197 contains a time-based blind SQL injection vulnerability in the language update function where the language id parameter is concatenated unescaped into the WHERE clause of an UPDATE statement. An authenticated administrator with basic settings permission can inject...
Controlled Decoding Attacks on Black-Box LLMs
Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to model weights or numerical token probabilities and therefore do not apply to interfaces that return only sampled text. Reconstructing...
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs Via Weight Orthogonalisation
Backdoor attacks can be implanted in Large Language Models LLMs during training, causing unwanted behaviour when a trigger appears in the input. Existing backdoor defences for LLMs attempt to remove the backdoor but inadvertently shift the model's output distribution to benign prompts, which can...
Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance
When a prompt injection attack succeeds, a Large Language Model LLM abandons its assigned system role to comply with an adversarial instruction. While prior work has extensively quantified how often this occurs, we ask a more fundamental question: where inside the network does the model actually...
Selective Channel Restoration for Backdoored Vision-Language Models
Vision-language models VLMs exhibit strong multimodal capabilities but remain vulnerable to backdoors implanted through poisoned fine-tuning data. Existing defenses often require extensive parameter updates during fine-tuning or incur per-query overhead during inference. To address these...
The Geometry of Harmfulness in Multi-Turn Attacks
Large language models LLMs remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear how harmfulness and refusal representations evolve over the course of multi-turn attacks, and why single-turn defenses are less effective in multi-tur...
GO-2026-6539 nginx ignition has ParseAcceptLanguage `_` separator bypass that enables ~75x CPU amplification via Accept-Language header in i18nMiddleware in github.com/lucasdillmann/nginx-ignition
nginx ignition has ParseAcceptLanguage separator bypass that enables 75x CPU amplification via Accept-Language header in i18nMiddleware in github.com/lucasdillmann/nginx-ignition...
PT-2026-99959
FreePBX is an open source IP PBX. Prior to versions 16.0.10 and 17.0.5, a critical vulnerability exists in the sound language upload and conversion functionality that allows an authenticated attacker to perform arbitrary file writes, leading directly to remote code execution RCE. Authentication...
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
Language-model agents increasingly use tools to act on external systems. Earlier actions can alter files, permissions, database records, or other state, making a later routine-looking action harmful. Yet the visible interaction may not reveal the underlying state needed to assess that action. We...
CVE-2026-54675: Improper Limitation of a Pathname to a Restricted Directory
FreePBX is an open source IP PBX. Prior to versions 16.0.10 and 17.0.5, a critical vulnerability exists in the sound language upload and conversion functionality that allows an authenticated attacker to perform arbitrary file writes, leading directly to remote code execution RCE. Authentication...
Distillation Defenses Easily Break after Reinforcement Learning
Distillation attacks copy the reasoning capabilities of closed-source large language models, allowing bad actors to replicate state-of-the-art performance at low cost. Attackers systematically collect a large volume of frontier model reasoning traces and then train i.e., "distill" their own model...
FinRT: Distilling Adaptive Red-Teaming Strategies into Reusable Adversarial Generators in Consumer Finance
In regulated industries like consumer finance, seemingly harmless user queries can exploit large language model vulnerabilities, triggering safety failures and pushing responses dangerously close to policy limits. Existing automated red-teaming methods trade off attack effectiveness against...
No Free Efficiency: Revisiting the Trade-Off between Training Efficiency and Model Vulnerability
Training efficiency has become the central driver of recent progress in foundation models. To overcome the massive computational and data requirements of large-scale training, researchers increasingly adopt strategies such as selective data sampling, efficient pre-training, and simplified...
API Secrets Should Never Become Tokens in the LLM's Vocabulary
Tool-using large language model LLM agents turn credential hygiene from a storage problem into an execution-security problem. A key pasted into a prompt, or embedded in a system prompt or tool configuration, crosses from an authentication boundary into a data pipeline, where it may persist in...
sentinel
Sentinel · Security Operations & Management Console Lightwe...
CLEANSTART-2026-WV65132 Integer Overflow or Wraparound vulnerability in Apache Thrift TFramedTransport Go language implementation This issue affects Apache Thrift: before 0
Security vulnerability affects the loki package. Integer Overflow or Wraparound vulnerability in Apache Thrift TFramedTransport Go language implementation This issue affects Apache Thrift: before 0...
PT-2026-99374
Name of the Vulnerable Software and Affected Versions Kyverno versions 1.16.0 through 1.19.0 Description The software registers the globalcontext.Lib Common Expression Language CEL library in its policy environment without restricting it to the policy's namespace. This differs from other librarie...
CVE-2026-100380 Reflected XSS in Wikibase Special:SetLabel language validation
Improper Neutralization of Input During Web Page Generation XSS or 'Cross-site Scripting' vulnerability in Wikimedia Foundation Mediawiki - Wikibase Extension allows Cross-Site Scripting XSS. This issue affects Mediawiki - Wikibase Extension: from before 1.46.1, 1.45.5, 1.43.10...
CVE-2026-100380 Reflected XSS in Wikibase Special:SetLabel language validation
Improper Neutralization of Input During Web Page Generation XSS or 'Cross-site Scripting' vulnerability in Wikimedia Foundation Mediawiki - Wikibase Extension allows Cross-Site Scripting XSS. This issue affects Mediawiki - Wikibase Extension: from before 1.46.1, 1.45.5, 1.43.10...