arXiv Machine Learning
Jun 18
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
arXiv:2606. 19023v1 Announce Type: cross Abstract: The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces.
Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
Amulet is a Python library designed to evaluate how machine learning defenses interact with various risks, including both intended and unintended effects. It incorporates representative attacks, defenses, and metrics, and its modular architecture allows easy extension to new modules. The library provides a consistent, user-friendly API for inputs and outputs, enabling systematic studies of defense interactions across multiple risk domains.
Related stories
arXiv AI
Nov 2
RiskyPy: Toward Model-Calibrated Prompt Generation for Joint Security and Functionality Evaluation of LLM-Generated Code
arXiv:2610.40735v1 Announce Type: cross Abstract: Evaluating approaches that improve the security of LLM code generation requires datasets that jointly assess security and functionality and remain ad...
Hugging Face Trending Papers
Jun 17
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defenses.
arXiv Machine Learning
Sep 21
Identifying Security Platform Product Abuse with Machine Learning
arXiv:2609.21303v1 Announce Type: cross Abstract: Product abuse is an individually rare, but growing, problem across the SaaS industry. Highly sophisticated threat actors can misuse security platform...
arXiv Machine Learning
Jul 20
Code-Poisoning Property Inference Attacks
arXiv:2607. 15970v1 Announce Type: cross Abstract: The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning (ML) models using available code quickly.
arXiv AI
Jul 21
A Survey on Unlearnable Data
arXiv:2503. 23536v3 Announce Type: replace-cross Abstract: Unlearnable data (ULD) has emerged as an innovative defense technique to prevent machine learning models from learning meaningful patterns from specific data, thus protecting data privacy and security.
arXiv AI
Jul 16
Adversarial Prompting Framework for AI Safety Assessment
arXiv:2607. 13453v1 Announce Type: cross Abstract: Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years.
arXiv Machine Learning
Oct 15
Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
arXiv:2610.19766v1 Announce Type: cross Abstract: Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational networks, their dependence on...
arXiv AI
Oct 12
Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal
The paper examines how fine‑tuned defenses against prompt injection in large language models can be audited before deployment. By leveraging intermediate checkpoints from the fine‑tuning process, the authors create strong optimization‑based attacks (e.g., GCG and BEAST) that dramatically increase attack success rates—from near zero to up to 96%—against state‑of‑the‑art defenses. This demonstrates that current empirical evaluations often overestimate robustness and that pre‑deployment stress‑testing can uncover real vulnerabilities.
arXiv AI
Sep 30
Adversarial Defense in Cybersecurity: A Systematic Review of GANs for Threat Detection and Mitigation
arXiv:2509.20411v3 Announce Type: replace-cross Abstract: Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act a...
arXiv Machine Learning
Oct 8
Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
The paper examines the vulnerability of open‑weight large language model safeguards that aim to block harmful usage by assuming new harmful behavior arises only through fine‑tuning. It demonstrates that simple, low‑cost attacks—abliteration and prefilling—can significantly increase attack success rates across multiple benchmarks, and proposes an abliteration‑resistant tuning (ART) method that mitigates these attacks. The study shows that safeguarding defenses must be evaluated against a broader range of attack strategies beyond fine‑tuning.
arXiv AI
Jun 9
Safe-RULE: Safe Reinforcement UnLEarning
arXiv:2606. 09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems.