Related papers: Mitigating False Positives in Static Memory Safety…
Although safety stock optimisation has been studied for more than 60 years, most companies still use simplistic means to calculate necessary safety stock levels, partly due to the mismatch between existing analytical methods' emphases on…
As safety violations can lead to severe consequences in real-world robotic applications, the increasing deployment of Reinforcement Learning (RL) in robotic domains has propelled the study of safe exploration for reinforcement learning…
The massive scale of modern AI accelerators presents critical challenges to traditional fault assessment methodologies, which face prohibitive computational costs and provide poor coverage of critical failure modes. This paper introduces…
Cyber threat intelligence (CTI) analysts routinely convert noisy, unstructured security artifacts into standardized, automation-ready representations. Although large language models (LLMs) show promise for this task, existing approaches…
Recent advances in vision-language models (VLMs) have improved Chest X-ray (CXR) interpretation in multiple aspects. However, many medical VLMs rely solely on supervised fine-tuning (SFT), which optimizes next-token prediction without…
The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliability applications,…
Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either address safety requirements under the assumption of no…
This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…
Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce…
Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…
We present a reinforcement learning (RL) approach for robust optimisation of risk-aware performance criteria. To allow agents to express a wide variety of risk-reward profiles, we assess the value of a policy using rank dependent expected…
The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical…
Ensuring safety is a crucial challenge when deploying reinforcement learning (RL) to real-world systems. We develop confidence-based safety filters, a control-theoretic approach for certifying state safety constraints for nominal policies…
Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residual RL is more sample-efficient than finetuning the entire…
Rust is a modern programming language that guarantees memory safety and the absence of data races with a strong type system. We present RustyDL, a program logic for Rust, as a foundation for an auto-interactive, deductive verification tool…
A major challenge of reinforcement learning (RL) in real-world applications is the variation between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a meta-policy that adapts to new tasks. Standard MRL methods…
Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple…
The Rust programming language is becoming increasingly popular among systems programmers due to its efficient performance and robust memory safety guarantees. Rust employs an ownership model to ensure this guarantee by allowing each value…
Reinforcement learning (RL)-based driver assistance systems seek to improve fuel consumption via continual improvement of powertrain control actions considering experiential data from the field. However, the need to explore diverse…
Reinforcement learning (RL) fine-tuning transforms large language models while creating a vulnerability we experimentally verify: Our experiment shows that malicious RL fine-tuning dismantles safety guardrails with remarkable efficiency,…