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

Ransomware represents a pervasive threat, traditionally countered at the operating system, file-system, or network levels. However, these approaches often introduce significant overhead and remain susceptible to circumvention by attackers.…

Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or…

Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but also raising critical safety and societal concerns. In particular, open-weight MLLMs may be…

The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Training machine learning models requires the storage of large datasets, which often contain sensitive or private data. Storing data is associated with a number of potential risks which increase over time, such as database breaches and…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query it with their data via an API. However, if the user's input…

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

Machine learning (ML) models show strong promise for new biomedical prediction tasks, but concerns about trustworthiness have hindered their clinical adoption. In particular, it is often unclear whether a model relies on true clinical cues…

This paper investigates the resilience of a ResNet-50 image classification model under two prominent security threats: Fast Gradient Sign Method (FGSM) adversarial attacks and malicious payload injection. Initially, the model attains a…

As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

Malware detection and analysis are active research subjects in cybersecurity over the last years. Indeed, the development of obfuscation techniques, as packing, for example, requires special attention to detect recent variants of malware.…

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may…

Many of today's machine learning (ML) systems are not built from scratch, but are compositions of an array of {\em modular learning components} (MLCs). The increasing use of MLCs significantly simplifies the ML system development cycles.…

A growing ecosystem of large, open-source foundation models has reduced the labeled data and technical expertise necessary to apply machine learning to many new problems. Yet foundation models pose a clear dual-use risk, indiscriminately…

Safety mechanisms in LLMs remain vulnerable to attacks that reframe harmful requests through culturally coded structures. We introduce Adversarial Tales, a jailbreak technique that embeds harmful content within cyberpunk narratives and…

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to…