Related papers: Defending Hash Tables from Subterfuge with Depth C…
This paper considers the problem of resilient distributed optimization and stochastic machine learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has a local cost function. The agents…
We quantify the threat of network adversaries to inducing \emph{network overload} through \emph{routing attacks}, where a subset of network nodes are hijacked by an adversary. We develop routing attacks on the hijacked nodes for two…
Today, Internet becomes the essential part of our lives. Over 90 percent of the ecommerce is developed on the Internet. A security algorithm became very necessary for producer client transactions assurance and the financial applications…
Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically…
In adversarial patrolling games, a mobile Defender strives to discover intrusions at vulnerable targets initiated by an Attacker. The Attacker's utility is traditionally defined as the probability of completing an attack, possibly weighted…
Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…
RowHammer vulnerabilities pose a significant threat to modern DRAM-based systems, where rapid activation of DRAM rows can induce bit-flips in neighboring rows. To mitigate this, state-of-the-art host-side RowHammer mitigations typically…
A hash table is said to be open-addressed (or non-obliviously open-addressed) if it stores elements (and free slots) in an array with no additional metadata. Intuitively, open-addressed hash tables must incur a space-time tradeoff: The…
Advances in deep neural networks (DNNs) have significantly contributed to the development of real-time video processing applications. Efficient scheduling of DNN workloads in cloud-hosted inference systems is crucial to minimizing serving…
Blockchain is a distributed ledger, which is protected against malicious modifications by means of cryptographic tools, e.g. digital signatures and hash functions. One of the most prominent applications of blockchains is cryptocurrencies,…
Decentralized machine learning (DL) has been receiving an increasing interest recently due to the elimination of a single point of failure, present in Federated learning setting. Yet, it is threatened by the looming threat of Byzantine…
This paper investigates the problem of synthesizing proactive defense systems in which the defender can allocate deceptive targets and modify the cost of actions for the attacker who aims to compromise security assets in this system. We…
We present SmartShards: a new sharding algorithm for improving Byzantine tolerance and churn resistance in blockchains. Our algorithm places a peer in multiple shards to create an overlap. This simplifies cross-shard communication and shard…
To defend against Byzantine attacks in decentralized learning, most existing methods rely on robust aggregation rules to mitigate the influence of malicious machines. However, these strategies inherently introduce bias, leading to inexact…
Fault injection attacks are a potent threat against embedded implementations of neural network models. Several attack vectors have been proposed, such as misclassification, model extraction, and trojan/backdoor planting. Most of these…
Database query processing requires algorithms for duplicate removal, grouping, and aggregation. Three algorithms exist: in-stream aggregation is most efficient by far but requires sorted input; sort-based aggregation relies on external…
We study distributed optimization in the presence of Byzantine adversaries, where both data and computation are distributed among $m$ worker machines, $t$ of which may be corrupt. The compromised nodes may collaboratively and arbitrarily…
Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, but its robustness is threatened by Byzantine behaviors such as data and model poisoning. Existing defenses face fundamental…
Neural network policies trained using Deep Reinforcement Learning (DRL) are well-known to be susceptible to adversarial attacks. In this paper, we consider attacks manifesting as perturbations in the observation space managed by the…
Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks.…