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

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

Many state-of-the-art adversarial training methods for deep learning leverage upper bounds of the adversarial loss to provide security guarantees against adversarial attacks. Yet, these methods rely on convex relaxations to propagate lower…

Current deep learning architectures are growing larger in order to learn from complex datasets. These architectures require giant matrix multiplication operations to train millions of parameters. Conversely, there is another growing trend…

Developing a safe, stable, and efficient obstacle avoidance policy in crowded and narrow scenarios for multiple robots is challenging. Most existing studies either use centralized control or need communication with other robots. In this…

State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on inputs with predefined triggers while retaining performance…

Deep neural networks have become the driving force of modern image recognition systems. However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these systems. In this paper,…

Rowhammer is a hardware vulnerability in DRAM memory, where repeated access to memory can induce bit flips in neighboring memory locations. Being a hardware vulnerability, rowhammer bypasses all of the system memory protection, allowing…

Rowhammer attacks that corrupt level-1 page tables to gain kernel privilege are the most detrimental to system security and hard to mitigate. However, recently proposed software-only mitigations are not effective against such kernel…

Tackling overestimation in $Q$-learning is an important problem that has been extensively studied in single-agent reinforcement learning, but has received comparatively little attention in the multi-agent setting. In this work, we…

DRAM cells are susceptible to Data-Disturbance Errors (DDE), which can be exploited by an attacker to compromise system security. Rowhammer is a well-known DDE vulnerability that occurs when a row is repeatedly activated. Rowhammer can be…

The increasing density of modern DRAM has heightened its vulnerability to Rowhammer attacks, which induce bit flips by repeatedly accessing specific memory rows. This paper presents an analysis of bit flip patterns generated by advanced…

This retrospective paper describes the RowHammer problem in Dynamic Random Access Memory (DRAM), which was initially introduced by Kim et al. at the ISCA 2014 conference~\cite{rowhammer-isca2014}. RowHammer is a prime (and perhaps the…

In modern containerized cloud environments, the adoption of RDMA (Remote Direct Memory Access) has expanded to reduce CPU overhead and enable high-performance data exchange. Achieving this requires strong performance isolation to ensure…

Rowhammer is a security vulnerability that allows unauthorized attackers to induce errors within DRAM cells. To prevent fault injections from escalating to successful attacks, a widely accepted mitigation is implementing fault checks on…

This paper studies the problem of mitigating reactive jamming, where a jammer adopts a dynamic policy of selecting channels and sensing thresholds to detect and jam ongoing transmissions. The transmitter-receiver pair learns to avoid…

Consistent hashing is fundamental to distributed systems, but ring-based schemes can exhibit high peak-to-average load ratios unless they use many virtual nodes, while multi-probe methods improve balance at the cost of scattered memory…

The Rugged Metropolis (RM) algorithm is a biased updating scheme, which aims at directly hitting the most likely configurations in a rugged free energy landscape. Details of the one-variable (RM$_1$) implementation of this algorithm are…

Micro-architectural attacks use information leaked through shared resources to break hardware-enforced isolation. These attacks have been used to steal private information ranging from cryptographic keys to privileged Operating System (OS)…

Convolutional neural networks have demonstrated high accuracy on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. For example, imperceptible perturbations added to clean images can cause…

Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current approaches, which typically assume that regularization…