Related papers: Run-Off Election: Improved Provable Defense agains…
The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…
Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poisoning attacks when malicious clients send false updates to the…
Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or expensive. When deployment environments are expected to…
Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer an end-to-end solution. To overcome this, we propose a…
Sparse or $\ell_0$ adversarial attacks arbitrarily perturb an unknown subset of the features. $\ell_0$ robustness analysis is particularly well-suited for heterogeneous (tabular) data where features have different types or scales.…
Real-world data is usually segmented by attributes and distributed across different parties. Federated learning empowers collaborative training without exposing local data or models. As we demonstrate through designed attacks, even with a…
For model privacy, local model parameters in federated learning shall be obfuscated before sent to the remote aggregator. This technique is referred to as \emph{secure aggregation}. However, secure aggregation makes model poisoning attacks…
While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic…
Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks (DNN) to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to…
In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural…
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…
Conditional decision generation with diffusion models has shown powerful competitiveness in reinforcement learning (RL). Recent studies reveal the relation between energy-function-guidance diffusion models and constrained RL problems. The…
Reinforcement Learning (RL)-based motion planning has recently shown the potential to outperform traditional approaches from autonomous navigation to robot manipulation. In this work, we focus on a motion planning task for an evasive target…
Batch reinforcement learning enables policy learning without direct interaction with the environment during training, relying exclusively on previously collected sets of interactions. This approach is, therefore, well-suited for high-risk…
Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and model poisoning attacks (MPAs) that degrade global model…
Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with the initial training…
Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to data poisoning attacks. Existing attack strategies typically rely on locally uniform perturbations, which treat all samples…
Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…
Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…
Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to…