相关论文: The Maestro Attack: Orchestrating Malicious Flows …

Offline Reinforcement Learning from Human Feedback (RLHF) pipelines such as Direct Preference Optimization (DPO) train on a pre-collected preference dataset, which makes them vulnerable to preference poisoning attack. We study label flip…

A distributed denial-of-service (DDoS) attack can flood a victim site with malicious traffic, causing service disruption or even complete failure. Public-access sites like amazon or ebay are particularly vulnerable to such attacks, because…

Cyberthreats are a permanent concern in our modern technological world. In the recent years, sophisticated traffic analysis techniques and anomaly detection (AD) algorithms have been employed to face the more and more subversive adversarial…

Federated Learning (FL) is a distributed paradigm aimed at protecting participant data privacy by exchanging model parameters to achieve high-quality model training. However, this distributed nature also makes FL highly vulnerable to…

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…

Federated learning is a promising approach for training machine learning models while preserving data privacy. However, its distributed nature makes it vulnerable to backdoor attacks, particularly in NLP tasks, where related research…

Federated embodied agent learning protects the data privacy of individual visual environments by keeping data locally at each client (the individual environment) during training. However, since the local data is inaccessible to the server…

Distributed denial of service(DDos) attack is ongoing dangerous threat to the Internet. Commonly, DDos attacks are carried out at the network layer, e.g. SYN flooding, ICMP flooding and UDP flooding, which are called Distributed denial of…

Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is…

Distributed denial of service (DDoS) attacks are a constant threat for services in the Internet. This year, the record for the largest DDoS attack ever observed was set at 1.7 Tbps. Meanwhile, detection and mitigation mechanisms are still…

The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. Though prior work has explored backdoor attacks against diffusion models for image or unconditional graph generation,…

A distributed denial-of-service (DDoS) attack is an attack wherein multiple compromised computer systems flood the bandwidth and/or resources of a target, such as a server, website or other network resource, and cause a denial of service…

Federated learning (FL) attempts to train a global model by aggregating local models from distributed devices under the coordination of a central server. However, the existence of a large number of heterogeneous devices makes FL vulnerable…

Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are…

Federated learning is a popular strategy for training models on distributed, sensitive data, while preserving data privacy. Prior work identified a range of security threats on federated learning protocols that poison the data or the model.…

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for…

Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one…

Deep Neural Network (DNN) models have vulnerabilities related to security concerns, with attackers usually employing complex hacking techniques to expose their structures. Data poisoning-enabled perturbation attacks are complex adversarial…

A malicious attempt to exhaust a victim's resources to cause it to crash or halt its services is known as a distributed denial-of-service (DDoS) attack. DDOS attacks stop authorized users from accessing specific services available on the…