相关论文: Preference Poisoning Attacks on Reward Model Learn…

Traditional approaches to ranking in web search follow the paradigm of rank-by-score: a learned function gives each query-URL combination an absolute score and URLs are ranked according to this score. This paradigm ensures that if the score…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

This work tackles the problem of overoptimization in reinforcement learning from human feedback (RLHF), a prevalent technique for aligning models with human preferences. RLHF relies on reward or preference models trained on \emph{fixed…

Federated Learning (FL) is a technique that allows multiple parties to train a shared model collaboratively without disclosing their private data. It has become increasingly popular due to its distinct privacy advantages. However, FL models…

This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the data in a malicious manner can drastically deteriorate the…

We reformulate explanation quality assessment as a ranking problem rather than a generation problem. Instead of optimizing models to produce a single "best" explanation token-by-token, we train reward models to discriminate among multiple…

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed…

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving. In the side of the…

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…

This review paper takes a comprehensive look at malicious attacks against FL, categorizing them from new perspectives on attack origins and targets, and providing insights into their methodology and impact. In this survey, we focus on…

We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Offline reinforcement learning refers to the process of learning policies from fixed datasets, without requiring additional environment interaction. However, it often relies on well-defined reward functions, which are difficult and…

Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…

Federated Recommendation (FR) has received considerable popularity and attention in the past few years. In FR, for each user, its feature vector and interaction data are kept locally on its own client thus are private to others. Without the…