Related papers: MAD: Memory Allocation meets Software Diversity

Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused…

It is becoming increasingly imperative to design robust ML defenses. However, recent work has found that many defenses that initially resist state-of-the-art attacks can be broken by an adaptive adversary. In this work we take steps to…

Caches have been exploited to leak secret information due to the different times they take to handle memory accesses. Cache timing attacks include non-speculative cache side and covert channel attacks and cache-based speculative execution…

Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially…

Disaggregated memory leverages recent technology advances in high-density, byte-addressable non-volatile memory and high-performance interconnects to provide a large memory pool shared across multiple compute nodes. Due to higher memory…

With deep learning deployed in many security-sensitive areas, machine learning security is becoming progressively important. Recent studies demonstrate attackers can exploit system-level techniques exploiting the RowHammer vulnerability of…

Millions of new pieces of malicious software (i.e., malware) are introduced each year. This poses significant challenges for antivirus vendors, who use machine learning to detect and analyze malware, and must keep up with changes in the…

This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee. In stochastic bandit systems, the rewards may refer to the users' activities, which may…

Learning algorithms are being increasingly adopted in various applications. However, further expansion will require methods that work more automatically. To enable this level of automation, a more powerful solution representation is needed.…

It is often said that one of the biggest limitations on computer performance is memory bandwidth (i.e."the memory wall problem"). In this position paper, I argue that if historical trends in computing evolution (where growth in available…

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

We introduce robustness in \textit{restless multi-armed bandits} (RMABs), a popular model for constrained resource allocation among independent stochastic processes (arms). Nearly all RMAB techniques assume stochastic dynamics are precisely…

Recent research on backdoor stealthiness focuses mainly on indistinguishable triggers in input space and inseparable backdoor representations in feature space, aiming to circumvent backdoor defenses that examine these respective spaces.…

Today, with the continued growth in using information and communication technologies (ICT) for business purposes, business organizations become increasingly dependent on their information systems. Thus, they need to protect them from the…

In this paper, we consider the problem of resource allocation in the orthogonal frequency division multiple access system with single source and M untrusted users in presence of a friendly jammer. The jammer is used to improve either the…

Caching high-frequency reuse contents at the edge servers in the mobile edge computing (MEC) network omits the part of backhaul transmission and further releases the pressure of data traffic. However, how to efficiently decide the caching…

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more…

We propose a new variant of the Adam optimizer called MicroAdam that specifically minimizes memory overheads, while maintaining theoretical convergence guarantees. We achieve this by compressing the gradient information before it is fed…

Reconstruction-based anomaly detection models achieve their purpose by suppressing the generalization ability for anomaly. However, diverse normal patterns are consequently not well reconstructed as well. Although some efforts have been…

Active Directory (AD) is the default security management system for Windows domain networks. We study a Stackelberg game model between one attacker and one defender on an AD attack graph. The attacker initially has access to a set of entry…