相关论文: Making Belady-Inspired Replacement Policies More E…

In this fast-evolving area of LLMs, our paper discusses the significant security risk presented by prompt injection attacks. It focuses on small open-sourced models, specifically the LLaMA family of models. We introduce novel defense…

3D NAND flash memory with advanced multi-level cell techniques provides high storage density, but suffers from significant performance degradation due to a large number of read-retry operations. Although the read-retry mechanism is…

In a 2002 paper, Che and co-authors proposed a simple approach for estimating the hit rates of a cache operating the least recently used (LRU) replacement policy. The approximation proves remarkably accurate and is applicable to quite…

We show how to infer deterministic cache replacement policies using off-the-shelf automata learning and program synthesis techniques. For this, we construct and chain two abstractions that expose the cache replacement policy of any set in…

In this paper, we study the offline RL problem with linear function approximation. Our main structural assumption is that the MDP has low inherent Bellman error, which stipulates that linear value functions have linear Bellman backups with…

Pure exploration in episodic Reinforcement Learning has primarily focused on Best Policy Identification (BPI), which seeks to identify a (near)-optimal policy with high confidence. Motivated by practical settings where a ``good enough''…

Cache replacement algorithms are used to optimize the time taken by processor to process the information by storing the information needed by processor at that time and possibly in future so that if processor needs that information, it can…

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

High-throughput gene perturbation experiments can test several genetic interventions in parallel, yet experimental budgets remain limited. A central goal is hit discovery: identifying as many perturbations as possible whose phenotypic…

Decision-based attacks construct adversarial examples against a machine learning (ML) model by making only hard-label queries. These attacks have mainly been applied directly to standalone neural networks. However, in practice, ML models…

The effectiveness of AI debugging follows a predictable exponential decay pattern; most models lose 60-80% of their debugging capability within just 2-3 attempts, despite iterative debugging being a critical capability for practical code…

Due to an exponential increase in the number of cyber-attacks, the need for improved Intrusion Detection Systems (IDS) is apparent than ever. In this regard, Machine Learning (ML) techniques are playing a pivotal role in the early…

This paper considers the problem of detector tuning against false data injection attacks. In particular, we consider an adversary injecting false sensor data to maximize the state deviation of the plant, referred to as impact, whilst being…

Emerging vulnerabilities in machine learning (ML) models due to adversarial attacks raise concerns about their reliability. Specifically, evasion attacks manipulate models by introducing precise perturbations to input data, causing…

Persistent memory provides high-performance data persistence at main memory. Memory writes need to be performed in strict order to satisfy storage consistency requirements and enable correct recovery from system crashes. Unfortunately,…

We propose a symbolic execution method for analyzing the safety of software under fault attacks both accurately and efficiently. Fault attacks leverage physically injected hardware faults in an embedded system to break the safety of a…

For applications in worst-case execution time analysis and in security, it is desirable to statically classify memory accesses into those that result in cache hits, and those that result in cache misses. Among cache replacement policies,…

In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new…

This paper presents analytical techniques to improve redundancy and relevance assessment for precise selection of features in practical multi-class raw datasets. We propose a matrix-rank based $k$-medoids algorithm that guarantees to output…

Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these policies are increasingly being deployed in the real world, their robustness and potential…