FreeBSD Security Advisory - FreeBSD-SA-26:64.sysvsem

FreeBSD Security Advisory - Heap out-of-bounds access in semop2. An unprivileged local user can trigger an out-of-bounds access on kernel heap memory, potentially leading to privilege escalation...

FreeBSD Security Advisory - FreeBSD-SA-26:66.jail

FreeBSD Security Advisory - Multiple jail filesystem root escapes. A process in a jail that has received a directory file descriptor from another jail can use these techniques to escape the jail's filesystem root restriction...

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...

A Competing-Hazards Systematization of Loss of Control in Autonomous Agents

Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of human control. Yet incident reports and agent-safety evaluations describe these events differently, making it difficult to compare failures, trace...

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...

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...

ModalFidelity: Routing Modalities for Deepfake Detection on a Budget

Deepfakes no longer need to fake a whole video. Generators that read the transcript now alter only the few seconds in which a video's meaning turns, so a forgery hides in a small, unknown fraction of the video. Yet detectors still read every one-second window of both the audio and image streams,...

FreeBSD Security Advisory - FreeBSD-SA-26:68.openssl

FreeBSD Security Advisory - Out-of-bounds read in OpenSSL DTLS retransmission. The retransmitted message may include heap memory contents, disclosing them to the DTLS peer as plaintext handshake data. If the read reaches unmapped memory, the application crashes, resulting in a Denial of Service D...

Privacy in Personalized AI Is a System Property, Not Just a Model Property

In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broader systems that access, infer, and reuse user information across components and over time. While such use of user information is integral to...

Epson EH-TW5350 150075647YWWV110 Authentication Bypass

Epson EH-TW5350 version 150075647YWWV110 contains an authentication bypass vulnerability that may allow a remote attacker to cause denial of service via specially crafted HTTP requests...

A Function-Level Dataset of Vulnerable and Fixed Source Code in JavaScript and TypeScript

JavaScript and TypeScript are widely used in modern web development, making their security critical; however, automated vulnerability detection is often constrained by the availability of high-quality training data. Here we present JsVul, a dataset curated from seven major sources. Unlike generic...

Confidence-Guided Protocol IR for LLM-Aided Security Protocol Modeling

Large language models offer a promising interface for translating natural-language protocol descriptions into formal security models, but their outputs remain difficult to trust without expert validation. In this paper, we present a human-in-the-loop framework for generating Tamarin-verifiable...

Quantum Time-Lock Puzzles in the Quantum Random Oracle Model

A time-lock puzzle allows a sender to hide a message in a puzzle such that recovering the message requires substantially more sequential computation than the time required to generate the puzzle, even when parallel computation is allowed. Applications of time-lock puzzles include timed-release...

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...

One Pipeline Does Not Fit All: TAILOR, a Type- and State-Aware Framework for CVE Reproduction

Growing vulnerability disclosure and widespread software reuse increase security teams' need for reproducible evidence to diagnose vulnerabilities, validate patches, and build regression tests. Producing such evidence at scale requires automated end-to-end CVE reproduction. Existing methods...

FreeBSD Security Advisory - FreeBSD-SA-26:69.udp

FreeBSD Security Advisory - IPv6 UDP sendto2 bypasses jail loopback restriction. A process in a classic non-VNET jail can send UDP datagrams to services listening on the host's IPv6 loopback address, bypassing jail network isolation...

Xalgorix Autonomous AI Pentesting Agent 4.6.121

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Forensic-Aware Continual Adaptation for Image Forgery Localization

The rapid evolution of image manipulation techniques has raised growing public security concerns. Existing Image Forgery Localization IFL methods can accurately localize manipulated regions but are often unable to adapt to newly emerging forgeries. In real-world forensic scenarios, data typically...

Deep Learning Latency Attacks and Defenses: A Cross-Domain Survey of Availability Threats

Adversarial machine learning has focused mainly on integrity, but availability is an increasingly consequential complement. Latency attacks also energy-latency attacks increase inference-time work, energy, or response time, causing deadline misses, throughput collapse, or resource exhaustion in...

Quantum Leakage Resilience of Shamir Secret Sharing

We initiate the study of quantum leakage resilience of unmodified Shamir secret sharing over prime fields. A well-studied leakage model for Shamir's secret sharing classically is single-bit local leakage from each share. We consider its quantum analogue where, for each party, a local leakage...

Joern 4.0.641

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

Beyond the Headset: A Systematization of Knowledge on Extended Reality Privacy and Security in Healthcare

Extended reality XR systems are increasingly used in healthcare applications ranging from surgical planning to remote rehabilitation and mental health support. However, the rich streams of sensor, biometric, behavioral, and environmental data that enable these applications also introduce...

Practical Secrets Extraction against Black-Box LLMs

Large language models LLMs increasingly power autonomous coding agents such as Codex and Claude Code, yet their training corpora may contain confidential credentials exposed in public repositories or collected from private development artifacts, creating risks of memorization and subsequent...

SURE: Framework for Safety to Construct Trustworthy AI

Warning: This paper contains harmful and offensive text. Recently, large language models such as GPT-4, and Claude have revolutionized tasks in various domains. As the use of these large language models increases, people are increasingly concerned about AI safety and demand that large language...

Does the Unsafe Gradient Survive a Conversation? on the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single prompt. Gradient-based jailbreak detectors such as GradSafe were developed for single prompts: they score an input by the...

CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition

Text-to-image T2I models have substantially improved in language understanding, in-image text rendering, and visual composition, while their safety mechanisms do not always keep pace with these capabilities. This creates a cross-modal attack surface in which harmful semantics can remain...

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...

Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks

This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions outside the scope of their assigned task. We evaluate whether frontier models conduct supply-chain attacks against...

When Cyber Scoring Systems Diverge: An Empirical Comparison

Vulnerability scoring systems underpin cyber patch prioritization and risk management, but their comparative behavior is almost always assessed in the abstract, through correlation studies in IT vulnerability databases, rather than by the operational consequences they produce when embedded in a...

Behavior-Centric Malware Classification with Fine-Grained Malicious Logic Localization

Effective malware analysis requires understanding not only whether a program is malicious, but also which behaviors it exhibits and where those behaviors originate in the code. Existing machine-learning-based malware detectors largely operate as black boxes, providing limited insight into the...

Agent-Warden: EBPF-Based Kernel-Native Process-File Provenance Tracking for LLM Agents

LLM agents execute dynamically generated process and file operations that are often invisible to application-layer tracing. We present Agent-Warden, an extended Berkeley Packet Filter eBPF-based provenance monitor for tracking task and regular-file states across process creation, file access, and...

Efficient Linkage-Based Compartmentalization on CHERI

We present an efficient linkage-based model for in-process compartmentalization built on CHERI memory safety, which enables fine-grained compartmentalization of the entire UNIX user-space, scaling to 10K+ compartments on desktop systems. The model's "push-button" compartmentalization along existi...

SoK: A Large-Scale Empirical Study of Emulation-Based Dynamic Analysis Research for ARM Cortex-M Firmware (Extended Version)

Microcontroller MCU-based devices are increasingly pervasive, making efficient, scalable firmware security analysis critical. Recent firmware re-hosting work enables automated vulnerability assessment, yet two gaps remain. First, existing tools are evaluated on limited, heavily overlapping...

Pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation

Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks 13...

ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents

Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content to steer consequential input-filtering defenses. Multi-path consensus defenses still leave a high attack success rate because...

LogiC-Diff: Embedding Security Properties into AI-Enabled Cyber-Physical Systems

AI-enabled Cyber-Physical Systems CPS are highly vulnerable to adversarial and anomalous inputs, where small perturbations can induce cascading errors and unsafe control actions. Existing approaches, such as rule-based filtering, training-time regularization, or diffusion-based reconstruction,...

SecureVibe: Making Vibe Coding More Secure

As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. When investigating functionally correct but insecure solutions, we find that the insecure agent is less than half as likely to conduct effective...

NoMachine Arbitrary File Deletion

NoMachine versions prior to fixed releases 9.4.14 and 8.22.1 contain an external control of file path vulnerability that allows a local low-privileged attacker to delete arbitrary files as root...

Epson EH-TW5350 Firmware Update Verification Bypass

Epson EH-TW5350 contains a firmware update verification bypass vulnerability...

VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents

Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems LLM-ARS instantiate users and items as autonomous agents, whose semantic states are dynamically refined through a recurrent process known as collaborative reflection. While this mechanism improves...

Proof-Gated Signing: Solver-Checked Transaction Guards That Hold under State Drift for Onchain AI Agents

AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of defense is a pre-signing check: a static allowlist, an LLM reviewer, or a transaction simulation. All three share a gap: the check describes the chain...

SiYuan 3.8.3 MCP File Operations Path Traversal

SiYuan versions 3.8.0 through 3.8.3 contain an incorrect authorization issue in recursive MCP file operations. An authenticated administrator can bypass the sensitive-path guard to read protected descendants or overwrite them through archive extraction...

Backdoor Mitigation in Decentralized LLM Fine-Tuning

Decentralized large language model LLM fine-tuning lets organizations collaboratively train a shared LLM on data they cannot pool, without a central coordinator. In every round, each node exchanges a trainable adapter with its neighbors over a communication graph, and then aggregates them. This...

Security-Enhanced Seed-Based Weight Quantization for Large Language Models

Large language models LLMs incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-based compression methods reconstruct weights from compact pseudo-random representations but do not explicitly account for the non-uniform sensitivity ...

OpenSSL Security Advisory 20260929

OpenSSL Security Advisory 20260929 - The DTLS retransmission logic does not correctly handle a handshake message write that is suspended part-way through. The retransmitted message can be read past the message buffer and the retransmission overwrites the internal state the suspended write needs t...

Concealing LLM-Based Multi-Agent Topology Via Phantom Structure Injection

Driven by the rapid advancement of large language models LLMs, LLM-based multi-agent systems MAS have emerged as a powerful paradigm for collaborative reasoning over complex tasks. A key design element of MAS is the communication topology, which governs information flow among agents and often...

Harvest Season for SLUB: From Io_uring Vulnerability to Novel Sheaf-Based Exploitation Techniques

The Linux kernel's push for higher I/O performance and more efficient memory management has introduced new mechanisms that, while improving performance, also open new attack surfaces. This research examines two of them together: the iouring subsystem and the sheaf/barn caching mechanism added to...

FreeBSD Security Advisory - FreeBSD-SA-26:65.kqueue

FreeBSD Security Advisory - Memory safety bugs in kqueue copy-on-fork implementation. An unprivileged local user may be able to exploit these races to escalate privileges...

Lights, Camera, Attack: Exploiting Temporal HDR Fusion with Pulsed Light

Modern cameras widely use temporal High Dynamic Range HDR to improve visibility by capturing a sequence of exposures with different integration times and fusing them into a single image. This process implicitly assumes that scene illumination remains sufficiently stable during capture. We introdu...

FreeBSD Security Advisory - FreeBSD-SA-26:67.ktls

FreeBSD Security Advisory - Remote DoS via receive-side kernel TLS. A remote TLS 1.3 peer can send a specially crafted record to trigger a kernel panic, resulting in a Denial of Service DoS...