Related papers: Bankrupting Sybil Despite Churn
Byzantine-robust learning has emerged as a prominent fault-tolerant distributed machine learning framework. However, most techniques focus on the static setting, wherein the identity of Byzantine workers remains unchanged throughout the…
There has been considerable and growing interest in applying machine learning for cyber defenses. One promising approach has been to apply natural language processing techniques to analyze logs data for suspicious behavior. A natural…
In various control task domains, existing controllers provide a baseline level of performance that -- though possibly suboptimal -- should be maintained. Reinforcement learning (RL) algorithms that rely on extensive exploration of the state…
Voting rules may implement the will of the society when all eligible voters vote, and only them. However, they may fail to do so when sybil (fake or duplicate) votes are present and when only some honest (non sybil) voters actively…
Due to data dependency and model leakage properties, Deep Neural Networks (DNNs) exhibit several security vulnerabilities. Several security attacks exploited them but most of them require the output probability vector. These attacks can be…
Reinforcement learning (RL)-based methods have achieved significant success in managing grid-interactive efficient buildings (GEBs). However, RL does not carry intrinsic guarantees of constraint satisfaction, which may lead to severe safety…
Today's intelligent computing environments, including Internet of Things, cloud computing and fog computing, allow many organizations around the world to optimize their resource allocation regarding time and energy consumption. Due to the…
Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing due to their bio-plausible and spike-driven characteristics. However, the robustness of SNNs in complex adversarial environments…
The Internet of Things (IoT) has been continuously rising in the past few years, and its potentials are now more apparent. However, transient data generation and limited energy resources are the major bottlenecks of these networks. Besides,…
Software Defined Networking (SDN) enables flexible and scalable network control and management. However, it also introduces new vulnerabilities that can be exploited by attackers. In particular, low-rate and slow or stealthy…
When learning common skills like driving, beginners usually have domain experts standing by to ensure the safety of the learning process. We formulate such learning scheme under the Expert-in-the-loop Reinforcement Learning where a guardian…
Routing attacks remain practically effective in the Internet today as existing countermeasures either fail to provide protection guarantees or are not easily deployable. Blockchain systems are particularly vulnerable to such attacks as they…
Strong physical unclonable function (PUF) is a promising solution for device authentication in resourceconstrained applications but vulnerable to machine learning attacks. In order to resist such attack, many defenses have been proposed in…
Electrical substations are becoming more prone to cyber-attacks due to increasing digitalization. Prevailing defense measures based on cyber rules are often inadequate to detect attacks that use legitimate-looking measurements. In this…
Pervasive AI increasingly depends on on-device learning systems that deliver low-latency and energy-efficient computation under strict resource constraints. Liquid State Machines (LSMs) offer a promising approach for low-power temporal…
In this work we study the problem of Byzantine-robust learning when data among clients is heterogeneous. We focus on poisoning attacks targeting the convergence of SGD. Although this problem has received great attention; the main Byzantine…
Named Entity Recognition (NER) is a cornerstone NLP task while its robustness has been given little attention. This paper rethinks the principles of NER attacks derived from sentence classification, as they can easily violate the label…
Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools for a multi-turn information-seeking process autonomously. However, we identify a critical…
The remarkable capabilities of Large Language Models (LLMs) have raised significant safety concerns, particularly regarding "jailbreak" attacks that exploit adversarial prompts to bypass safety alignment mechanisms. Existing defense…
Training modern neural networks or models typically requires averaging over a sample of high-dimensional vectors. Poisoning attacks can skew or bias the average vectors used to train the model, forcing the model to learn specific patterns…