Related papers: Towards Reinforcement Learning for Exploration of …

Transient execution side-channel attacks, such as Spectre, have been shown to break almost all isolation primitives. We introduce a new security property we call relaxed microarchitectural isolation (RMI) that allows sensitive programs that…

The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches,…

The specification synthesis task aims to automatically generate specifications, together with any necessary auxiliary verification annotations, for existing programs. This task is important because such specifications serve as behavioral…

Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with…

Building on previous work using reinforcement learning (RL) focused on identification of exfiltration paths, this work expands the methodology to include protocol and payload considerations. The former approach to exfiltration path…

Recently, out-of-order execution, an important performance optimization in modern high-end processors, has been revealed to pose a significant security threat, allowing information leaks across security domains. In particular, the Meltdown…

In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies, value functions, and dynamics models. Although powerful…

The iterative conditional branchings appear in various sensitive algorithms, like the modular exponentiation in the RSA cryptosystem or the scalar multiplication in ellipticcurve cryptography. In this paper, we abstract away the desirable…

Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this…

Despite their strong performance on reasoning tasks, large reasoning models (LRMs) often suffer from overthinking, producing unnecessarily long outputs and incurring high end-to-end latency, a significant limitation to their real-world…

Task-based programming models have demonstrated their efficiency in the development of scientific applications on modern high-performance platforms. They allow delegation of the management of parallelization to the runtime system (RS),…

This paper introduces Triosecuris, a formally verified defense against Spectre BTB, RSB, and PHT that combines CET-style hardware-assisted control-flow integrity with compiler-inserted speculative load hardening (SLH). Triosecuris is based…

We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples…

Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations rely on research prototypes and unrealistically small batch…

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we show that it is possible to conceptualize the creation of…

Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant drops even at moderate lengths. Yet, this early degradation has…

Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with sparse, delayed, and…

In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL). Our contributions are two-fold. First, we introduce a novel and coherent quantification of risk, namely composite risk, which quantifies…

The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or…