Related papers: Towards Reinforcement Learning for Exploration of …

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the…

Security vulnerability analysis of Integrated Circuits using conventional design-time validation and verification techniques (like simulations, emulations, etc.) is generally a computationally intensive task and incomplete by nature,…

Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to…

We present Speculative Rollout with Tree-Structured Cache (SRT), a simple, model-free approach to accelerate on-policy reinforcement learning (RL) for language models without sacrificing distributional correctness. SRT exploits the…

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…

Reinforcement learning (RL) has been widely applied to sequential decision making, where interpretability and performance are both critical for practical adoption. Current approaches typically focus on performance and rely on post hoc…

Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce unintuitive outputs. One key approach to verify and mitigate such robustness issues is to falsify…

Speculative decoding accelerates Large Language Model (LLM) inference by verifying multiple drafted tokens in parallel. However, for Mixture-of-Experts (MoE) models, this parallelism introduces a severe bottleneck: large draft trees…

Deep learning is gaining importance in many applications. However, Neural Networks face several security and privacy threats. This is particularly significant in the scenario where Cloud infrastructures deploy a service with Neural Network…

With the recent advancements in machine learning theory, many commercial embedded micro-processors use neural network models for a variety of signal processing applications. However, their associated side-channel security vulnerabilities…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Large language models (LLMs) acquire extensive prior knowledge through large-scale pretraining and can be further enhanced via supervised fine-tuning (SFT) or reinforcement learning (RL)-based post-training. A growing body of evidence has…

Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we…

Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large Reasoning Models (LRMs), which generate lengthy chains of…

Efficient reinforcement learning (RL) involves a trade-off between "exploitative" actions that maximise expected reward and "explorative'" ones that sample unvisited states. To encourage exploration, recent approaches proposed adding…

Deep reinforcement learning (DRL) has made significant achievements in many real-world applications. But these real-world applications typically can only provide partial observations for making decisions due to occlusions and noisy sensors.…

Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain opaque, hindering trust, debugging, and defensive preparedness. In high-stakes cybersecurity…

MicroScope, and microarchitectural replay attacks in general, take advantage of the characteristics of speculative execution to trap the execution of the victim application in an infinite loop, enabling the attacker to amplify a…

Due to delay and energy constraints, a cognitive radio may not be able to perform spectrum sensing in all available channels. Therefore, a sensing policy is needed to decide which channels to sense. The channel selection problem is the…

Specification-guided reinforcement learning (RL) provides a principled framework for encoding complex, temporally extended tasks using formal specifications such as linear temporal logic (LTL). While recent methods have shown promising…