38331 matches found
About the security content of visionOS 26.5
About the security content of visionOS 26.5 This document describes the security content of visionOS 26.5. About Apple security updates For our customers' protection, Apple doesn't disclose, discuss, or confirm security issues until an investigation has occurred and patches or releases are...
Guaranteed Jailbreaking Defense Via Disrupt-And-Rectify Smoothing
This paper proposes a guaranteed defense method for large language models LLMs to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel smoothing-based defense method, termed Disrupt-and-Rectify...
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing...
Skill Description Deception Attack against Task Routing in Internet of Agents
A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...
Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support
Engineering managers increasingly must decide how to introduce generative artificial intelligence AI, retrieval-augmented generation, and coding agents into high-risk operational functions without weakening accountability, privacy, cost discipline, or auditability. The central message of this stu...
Position: AI Security Policy Should Target Systems, Not Models
We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, parallel exploration, and evolutionary optimization. Together, our results demonstrate that both safety bypass of frontier models and software...
Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning
We address a fundamental challenge in cybersecurity operations of translating governance frameworks into actionable mitigation decisions under realistic resource constraints. Frameworks such as the NIST Cybersecurity Framework CSF provide widely adopted measures of organizational maturity, but do...
erebus
EREBUS Web application security assessment framework. For...
xfrm: esp: avoid in-place decrypt on shared skb frags
...
CVE-2026-8209
Gibbon versions before v30.0.01 are affected by a path traversal vulnerability resulting in DOS by attempting extraction of web application PHP files, failed .zip extraction results in deletion of the file and a DOS condition. Successful exploitation requires Teacher or higher privileges...
Hono has CSS Declaration Injection via Style Object Values in JSX SSR
Summary The JSX renderer escapes style attribute object values for HTML but not for CSS. Untrusted input in a style object value or property name can therefore inject additional CSS declarations into the rendered style attribute. The impact is limited to CSS and does not allow JavaScript executio...
Improper Encoding or Escaping of Output
Overview hono is an Ultrafast web framework for the Edges Affected versions of this package are vulnerable to Improper Encoding or Escaping of Output the styleObjectForEach and jsxAttr style serialization paths in the JSX runtime. An attacker can inject arbitrary CSS declarations by supplying...
Improper Validation of Specified Quantity in Input
Overview hono is an Ultrafast web framework for the Edges Affected versions of this package are vulnerable to Improper Validation of Specified Quantity in Input through the verify function in the JWT component. An attacker can supply a signed token with malformed nbf, exp, or iat claims, includin...
Use of Cache Containing Sensitive Information
Overview hono is an Ultrafast web framework for the Edges Affected versions of this package are vulnerable to Use of Cache Containing Sensitive Information through the cache process in the cache middleware. An attacker can cause responses to be cached or served incorrectly by sending requests tha...
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer. Recent methods demonstrate this risk, but they are usually...
Smart Contract Security beyond Detection
Smart contract security has progressed from vulnerability detection toward a broader research agenda that includes semantic reasoning, automated repair, adversarial robustness, and real-time exploit detection. This paper develops a capstone-oriented research narrative around four directions:...
PT-2026-39402
Name of the Vulnerable Software and Affected Versions Yii Framework versions prior to 2.0.55 Description Internal variables in the View::renderPhpFile and ErrorHandler::renderFile functions are not isolated, which can lead to parameter collisions that allow the overriding of included file paths...
phpVMS 8 访问控制错误漏洞
phpVMS 8 is an open-source aviation simulation and flight management application based on Laravel. Prior to version 7.0.6 of phpVMS, there was a access control vulnerability that stemmed from allowing unauthorized access to the legacy import feature...
AI Native Asset Intelligence
Modern security environments generate fragmented signals across cloud resources, identities, configurations, and third-party security tools. Although AI-native security assistants improve access to this data, they remain largely reactive: users must ask the right questions and interpret...