Related papers: PickleBall: Secure Deserialization of Pickle-based…

Multiple Instance Learning (MIL) is a sub-domain of classification problems with positive and negative labels and a "bag" of inputs, where the label is positive if and only if a positive element is contained within the bag, and otherwise is…

Model hijacking can cause significant accountability and security risks since the owner of a hijacked model can be framed for having their model offer illegal or unethical services. Prior works consider model hijacking as a training time…

Jailbreak transferability is the surprising phenomenon when an adversarial attack compromising one model also elicits harmful responses from other models. Despite widespread demonstrations, there is little consensus on why transfer is…

Machine Learning (ML)-powered apps are used in pervasive devices such as phones, tablets, smartwatches and IoT devices. Recent advances in collaborative, distributed ML such as Federated Learning (FL) attempt to solve privacy concerns of…

Hugging Face (HF) has established itself as a crucial platform for the development and sharing of machine learning (ML) models. This repository mining study, which delves into more than 380,000 models using data gathered via the HF Hub API,…

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

The rapidly evolving fields of Machine Learning (ML) and Artificial Intelligence have witnessed the emergence of platforms like Hugging Face (HF) as central hubs for model development and sharing. This experience report synthesizes insights…

Be it for a malicious or legitimate purpose, packing, a transformation that consists in applying various operations like compression or encryption to a binary file, i.e. for making reverse engineering harder or obfuscating code, is widely…

Imitation Learning has provided a promising approach to learning complex robot behaviors from expert demonstrations. However, learned policies can make errors that lead to safety violations, which limits their deployment in safety-critical…

Context: Open-source Pre-Trained Models (PTMs) provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs to support the reliable identification…

Modern model hubs, such as Hugging Face, store tens of petabytes of LLMs, with fine-tuned variants vastly outnumbering base models and dominating storage consumption. Existing storage reduction techniques -- such as deduplication and…

Ransomware remains a critical threat to cybersecurity, yet publicly available datasets for training machine learning-based ransomware detection models are scarce and often have limited sample size, diversity, and reproducibility. In this…

Allowing organizations to share their data for training of machine learning (ML) models without unintended information leakage is an open problem in practice. A promising technique for this still-open problem is to train models on the…

The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle…

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model,…

Diffusion models have attracted significant attention due to its exceptional data generation capabilities in fields such as image synthesis. However, recent studies have shown that diffusion models are vulnerable to copyright infringement…

Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query…

As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level vulnerabilities with real-world impact. This paper studies how adversarial attacks…