qiling

Qiling's use case, blog and related work Qiling is an advanced binary emulation framework, with the following features: Emulate multi-platforms: Windows, macOS, Linux, Android, BSD, UEFI, DOS, MBR. Emulate multi-architectures: 8086, X86, X8664, ARM, ARM64, MIPS, RISC-V, PowerPC. Support multiple...

CVE-2026-98713

In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Apply the fine-grained UNDEFs without FEATFGT FGUs don't actually require hardware support, so don't gate fgt trap config insertion on FGT. This is the only action required to allow FGUs always, as kvmcalculatetraps...

You Are the Trigger: Speaker-Activated Backdoors

Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an attacker to introduce triggers at inference time. We study a different threat model in which the attacker compromises the model during fine-tuning but h...

better_opts_attacks

May I have your attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks This repository contains code to run the ASTRA and ASTRA++ attacks that break SecAlign++, SecAlign, StruQ. This repository also contains some examples of generated attacks and attack...

CVE-2026-98713

In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Apply the fine-grained UNDEFs without FEATFGT FGUs don't actually require hardware support, so don't gate fgt trap config insertion on FGT. This is the only action required to allow FGUs always, as kvmcalculatetraps...

CVE-2026-98713 KVM: arm64: Apply the fine-grained UNDEFs without FEAT_FGT

In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Apply the fine-grained UNDEFs without FEATFGT FGUs don't actually require hardware support, so don't gate fgt trap config insertion on FGT. This is the only action required to allow FGUs always, as kvmcalculatetraps...

CVE-2026-98713 KVM: arm64: Apply the fine-grained UNDEFs without FEAT_FGT

In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Apply the fine-grained UNDEFs without FEATFGT FGUs don't actually require hardware support, so don't gate fgt trap config insertion on FGT. This is the only action required to allow FGUs always, as kvmcalculatetraps...

EUVD-2026-103967

In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Apply the fine-grained UNDEFs without FEATFGT FGUs don't actually require hardware support, so don't gate fgt trap config insertion on FGT. This is the only action required to allow FGUs always, as kvmcalculatetraps...

CVE-2026-98713

The Linux kernel addresses a vulnerability in KVM arm64 related to fine-grained UNDEFs (FGUs). The issue was caused by gating FGU trap configuration insertion on FEAT_FGT hardware support, even though FGUs do not require it. The fix ensures FGUs are applied consistently because kvm_calculate_trap...

mininode

Mininode Mininode is a CLI tool to reduce the attack surface of the Node.js applications by using static analysis of source code. It supports two modes of reduction 1 coarse, 2 fine. Mininode constructs the dependency graph modules and functions used of the application starting from main file, i....

refusal-relocates

Project Page · Quick start · Usage · CLI · Results · Reproduce · FAQ · Citation News 2026-09-28 Code released, with the run records and scripts that rebuild the paper's tables. Overview A few dozen harmful examples can remove an aligned model's refusal of harmful requests. Prior work localizes...

GHSA-CG6R-MPGC-H9MM GitHub CLI partially discloses authentication tokens in `gh auth status` output

Summary A security vulnerability has been identified in GitHub CLI where gh auth status could potentially print a portion of the authentication token in plaintext, depending on the lexical structure of the token. Affected users: - Authenticated users who ran gh auth status without the --show-toke...

EUVD-2026-54212

GitHub CLI partially discloses authentication tokens in gh auth status output...

SLDR

NeurIPS 2026 SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing 🔧 Environment Setup Clone the repository, create and activate the Conda environment, then install the required dependencies: git clone https://github.com/Stardust457/SLDR.git cd SLDR conda...

DeeCLIP

DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images ☀️ If you find this work useful for your research, please kindly star our repo and cite our paper! ☀️ TODO We are working hard on the following items: Release ArXiv paper Release training scripts...

ASCENT

ASCENT First-Order Optimal Fine-Tuning with Recalibration for Safety–Utility Co-Enhancement ASCENT derives a first-order optimal safety calibration update and the corresponding safety-related structure, optimizes downstream task updates to preserve safety-compatible components while suppressing...

GitLab 19.1 < 19.2.8 / 19.3 < 19.3.5 / 19.4 < 19.4.2 (CVE-2026-78335)

The version of GitLab installed on the remote host is affected by a vulnerability, as follows: - GitLab has remediated an issue in GitLab CE/EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an...

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies a model with a backdoor: hidden behavior that produces malicious outputs when a particular input pattern appears. Focusing on...

Sleeping Secrets: How Fine-Tuning Reawakens Privacy Risks in Language Models

Beyond adapting Large Language Models LLMs to specialized applications, fine-tuning has recently been shown to recover private information that is no longer accessible through direct queries. Previous fine-tuning recovery attacks, however, require genuine private supervision drawn from the same...

Backdoor Purification for LoRA-Tuned LLMs Via Null-Space Projection

With the rapid adoption of large language models LLMs and parameter-efficient fine-tuning PEFT methods, the risk of backdoor attacks has become more severe. Existing backdoor purification methods typically rely on at least one of the strong assumptions, such as prior knowledge of triggers, access...