Related papers: MAD: Memory Allocation meets Software Diversity

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…

For enterprise, personal and societal applications, there is now an increasing demand for automated authentication of identity from images using computer vision. However, current authentication technologies are still vulnerable to…

This paper is concerned with the defense of deep models against adversarial attacks. Inspired by the certificate defense approach, we propose a maximal adversarial distortion (MAD) optimization method for robustifying deep networks. MAD…

We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produced by normal or anomalous internal mechanisms. Mechanistic anomaly detection (MAD) aims…

Large language models (LLMs) have recently demonstrated impressive capabilities in reasoning tasks. Currently, mainstream LLM reasoning frameworks predominantly focus on scaling up inference-time sampling to enhance performance. In…

Memory errors continue to be a critical concern for programs written in low-level programming languages such as C and C++. Many different memory error defenses have been proposed, each with varying trade-offs in terms of overhead,…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

Cybersecurity often hinges on unpredictability, with a system's defenses being strongest when sensitive values and behaviors cannot be anticipated by attackers. This paper explores the concept of entropy injection-deliberately infusing…

A multi-user multi-armed bandit (MAB) framework is used to develop algorithms for uncoordinated spectrum access. The number of users is assumed to be unknown to each user. A stochastic setting is first considered, where the rewards on a…

We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents' beliefs. We introduce Distributionally Robust Adaptive…

In order to shed more light on how RowHammer affects modern and future devices at the circuit-level, we first present an experimental characterization of RowHammer on 1580 DRAM chips (408x DDR3, 652x DDR4, and 520x LPDDR4) from 300 DRAM…

The remarkable growth in large language model (LLM) capabilities has spurred exploration into multi-agent systems, with debate frameworks emerging as a promising avenue for enhanced problem-solving. These multi-agent debate (MAD)…

The next ubiquitous computing platform, following personal computers and smartphones, is poised to be inherently autonomous, encompassing technologies like drones, robots, and self-driving cars. Ensuring reliability for these autonomous…

Cyber vulnerability management is a critical function of a cybersecurity operations center (CSOC) that helps protect organizations against cyber-attacks on their computer and network systems. Adversaries hold an asymmetric advantage over…

DRAM-based main memory and its associated components increasingly account for a significant portion of application performance bottlenecks and power budget demands inside the computing ecosystem. To alleviate the problems of storage density…

Inter-VM RowHammer is an attack that induces a bitflip beyond the boundaries of virtual machines (VMs) to compromise a VM from another, and some software-based techniques have been proposed to mitigate this attack. Evaluating these…

RowHammer is a major read disturbance mechanism in DRAM where repeatedly accessing (hammering) a row of DRAM cells (DRAM row) induces bitflips in physically nearby DRAM rows (victim rows). To ensure robust DRAM operation, state-of-the-art…

A decade after its academic introduction, RowHammer (RH) remains a moving target that continues to challenge both the industry and academia. With its potential to serve as a critical attack vector, the ever-decreasing RH threshold now…

A deep learning system typically suffers from a lack of reproducibility that is partially rooted in hardware or software implementation details. The irreproducibility leads to skepticism in deep learning technologies and it can hinder them…