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...

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...

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...

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...

Jackrong LLM Fine-Tuning Guide path traversal vulnerability

The Jackrong LLM Fine-Tuning Guide contains a path traversal vulnerability. This vulnerability stems from the operation of the parameter “shardname” by the extractmtpheads function in the qwen-mtp-gguf/scripts/qwenmtpggufpipeline.py file within the MTP weightmap Handler component. It may lead to...

Jackrong LLM Fine-Tuning Guide path traversal vulnerability

The Jackrong LLM Fine-Tuning Guide contains a path traversal vulnerability. This vulnerability stems from improper handling of the weightmap parameter within the validateindexedtensors function in the file qwen-mtp-gguf/scripts/qwenmtpggufpipeline.py, potentially allowing remote attackers to...

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...

FedGraph: Defending Federated Large Language Model Fine-Tuning against Backdoor Attacks Via Graph-Based Aggregation

Federated fine-tuning of large language models LLMs allows multiple clients to collaboratively adapt models without sharing raw data, offering strong privacy benefits. However, this setting is highly vulnerable to backdoor attacks, in which malicious clients manipulate their updates to induce...

Backdooring Acoustic Foundation Models for Physically Realizable Triggers

Acoustic foundation models AFMs have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speaker verification with minimal resources. However, the security of applications based on AFMs remains largely underexplored. Our work addresses this ga...

Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models

Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual information at release alone cannot universally certify slow recovery. Function-preserving reparameterizations leave information unchanged while altering gradient-descent geometry, so a...

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...

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...

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...

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...

RAISE: Reinforcing Access Control Policy Synthesis in LLMs Via Symbolic Evaluation

Translating natural-language access-control requirements into policies requires careful reasoning about permissions, constraints, and exceptions, and even frontier LLMs often produce policies that violate the intended authorization semantics. We construct CedarInstruct, to our knowledge the first...

Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language Models

JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approaches such as Static Application Security Testing SAST tools often fail to identify many real-world vulnerabilities when applied to isolated code...

Benchmarking LLMs for Threat Level Determination

The fast progress of large language models LLMs opens new opportunities in the management of cyber threat intelligence, but their reliability for operational tasks remains unclear. In this work, we benchmark LLMs on the task of threat level determination. First, we construct a curated dataset...