相关论文: Randomized Line-to-Row Mapping for Low-Overhead Ro…

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores while violating human intent. Existing mitigations rely on…

Robust header compression (ROHC), critically positioned between the network and the MAC layers, plays an important role in modern wireless communication systems for improving data efficiency. This work investigates bi-directional ROHC…

Hierarchical matrix approximations have gained significant traction in the machine learning and scientific community as they exploit available low-rank structures in kernel methods to compress the kernel matrix. The resulting compressed…

Machine learning (ML) models serve as powerful tools for threat detection and mitigation; however, they also introduce potential new risks. Adversarial input can exploit these models through standard interfaces, thus creating new attack…

Rowhammer has drawn much attention from both academia and industry in the past years as rowhammer exploitation poses severe consequences to system security. Since the first comprehensive study of rowhammer in 2014, a number of rowhammer…

Deep learning (DL) methods have become the state-of-the-art for reconstructing sub-sampled magnetic resonance imaging (MRI) data. However, studies have shown that these methods are susceptible to small adversarial input perturbations, or…

Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal poisoning attacks, which can be formulated as bilevel…

This paper presents a novel repeater insertion algorithm for interconnect power minimization. The novelty of our approach is in the judicious integration of an analytical solver and a dynamic programming based method. Specifically, the…

The RowHammer vulnerability in DRAM is a critical threat to system security. To protect against RowHammer, vendors commit to security-through-obscurity: modern DRAM chips rely on undocumented, proprietary, on-die mitigations, commonly known…

Fast and reliable obstacle avoidance is an important task for mobile robots. In this work, we propose an efficient reactive system that provides high-quality obstacle avoidance while running at hundreds of hertz with minimal resource usage.…

In order to mitigate the distance reduction attack in Ultra-Wide Band (UWB) ranging, this paper proposes a secure ranging scheme based on a random time-hopping mechanism without redundant signaling overhead. Additionally, a secure ranging…

We propose a new RowHammer mitigation mechanism, CoMeT, that prevents RowHammer bitflips with low area, performance, and energy costs in DRAM-based systems at very low RowHammer thresholds. The key idea of CoMeT is to use low-cost and…

QUIC protocol is primarily designed to optimize web performance and security. However, previous research has pointed out that it is vulnerable to handshake flooding attacks. Attackers can send excessive volume of handshaking requests to…

Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understood. We introduce the Attention Redistribution Attack (ARA),…

Backdoor attacks pose severe threats to machine learning systems, prompting extensive research in this area. However, most existing work focuses on single-target All-to-One (A2O) attacks, overlooking the more complex All-to-X (A2X) attacks…

In the past decade, many vulnerabilities were discovered in microarchitectures which yielded attack vectors and motivated the study of countermeasures. Further, architectural and physical imperfections in DRAMs led to the discovery of…

Reinforcement learning (RL) has achieved remarkable success across diverse domains, enabling autonomous systems to learn and adapt to dynamic environments by optimizing a reward function. However, this reliance on reward signals creates a…

Memory tiering systems seek cost-effective memory scaling by adding multiple tiers of memory. For maximum performance, frequently accessed (hot) data must be placed close to the host in faster tiers and infrequently accessed (cold) data can…

In swarm robotics, confrontation including the pursuit-evasion game is a key scenario. High uncertainty caused by unknown opponents' strategies, dynamic obstacles, and insufficient training complicates the action space into a hybrid…