相关论文: Fake Resume Attacks: Data Poisoning on Online Job …

During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…

Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The extent of harm these attacks can produce in non-convex…

Existing model poisoning attacks to federated learning assume that an attacker has access to a large fraction of compromised genuine clients. However, such assumption is not realistic in production federated learning systems that involve…

Federated recommender systems (FedRec) have emerged as a promising approach to provide personalized recommendations while protecting user privacy. However, recent studies have shown their vulnerability to poisoning attacks, where malicious…

Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation of data-driven technologies. Feature selection has been…

Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art…

Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning systems clandestinely. While numerous backdoor attacks occur…

In this work, we propose a profile matching (or deanonymization) attack for unstructured online social networks (OSNs) in which similarity in graphical structure cannot be used for profile matching. We consider different attributes that are…

In this work, we present a data poisoning attack that confounds machine learning models without any manipulation of the image or label. This is achieved by simply leveraging the most confounding natural samples found within the training…

Recent advancements in Large Language Models (LLMs) have established them as agentic systems capable of planning and interacting with various tools. These LLM agents are often paired with web-based tools, enabling access to diverse sources…

AI-based code generators have become pivotal in assisting developers in writing software starting from natural language (NL). However, they are trained on large amounts of data, often collected from unsanitized online sources (e.g., GitHub,…

Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…

A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…

Federated learning is vulnerable to poisoning attacks by malicious adversaries. Existing methods often involve high costs to achieve effective attacks. To address this challenge, we propose a sybil-based virtual data poisoning attack, where…

Large Language Models (LLMs) are increasingly deployed via third-party system prompts downloaded from public marketplaces. We identify a critical supply-chain vulnerability: conditional system prompt poisoning, where an adversary injects a…

Phishing attacks are the most common type of cyber-attacks used to obtain sensitive information and have been affecting individuals as well as organisations across the globe. Various techniques have been proposed to identify the phishing…

Federated learning (FL) has become a popular tool for solving traditional Reinforcement Learning (RL) tasks. The multi-agent structure addresses the major concern of data-hungry in traditional RL, while the federated mechanism protects the…

To study the resilience of distributed learning, the "Byzantine" literature considers a strong threat model where workers can report arbitrary gradients to the parameter server. Whereas this model helped obtain several fundamental results,…

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…

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…