Related papers: De-Pois: An Attack-Agnostic Defense against Data P…
In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a…
Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…
Advances in distributed machine learning can empower future communications and networking. The emergence of federated learning (FL) has provided an efficient framework for distributed machine learning, which, however, still faces many…
Deep learning models are often trained on distributed, web-scale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionally introduce malicious examples to a model's performance. Our…
Regression models, which are widely used from engineering applications to financial forecasting, are vulnerable to targeted malicious attacks such as training data poisoning, through which adversaries can manipulate their predictions.…
Decentralized Federated Learning (DFL), a paradigm for managing big data in a privacy-preserved manner, is still vulnerable to poisoning attacks where malicious clients tamper with data or models. Current defense methods often assume…
We study data poisoning attacks in the online setting where training items arrive sequentially, and the attacker may perturb the current item to manipulate online learning. Importantly, the attacker has no knowledge of future training items…
Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…
Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number of poisoned…
Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…
Face recognition systems are robust against environmental changes and noise, and thus may be vulnerable to illegal authentication attempts using user face photos, such as spoofing attacks. To prevent such spoofing attacks, it is crucial to…
In recent years, a variety of effective neural network-based methods for anomaly and cyber attack detection in industrial control systems (ICSs) have been demonstrated in the literature. Given their successful implementation and widespread…
With the increase in machine learning (ML) applications in different domains, incentives for deceiving these models have reached more than ever. As data is the core backbone of ML algorithms, attackers shifted their interest toward…
This paper proposes and investigates a new approach for detecting and preventing several different types of poisoning attacks from affecting a centralized Federated Learning model via average accuracy deviation detection (AADD). By…
As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized data collaboratively without explicitly aggregating the data. Due to its ability to break data silos,…
Generally, regularization-based continual learning models limit access to the previous task data to imitate the real-world constraints related to memory and privacy. However, this introduces a problem in these models by not being able to…
The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…
Federated learning (FL) has become an emerging machine learning technique lately due to its efficacy in safeguarding the client's confidential information. Nevertheless, despite the inherent and additional privacy-preserving mechanisms…
Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key…
We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal…