Related papers: Neural Exec: Learning (and Learning from) Executio…

In this study, we investigate how a robot can generate novel and creative actions from its own experience of learning basic actions. Inspired by a machine learning approach to computational creativity, we propose a dynamic neural network…

Generating adversarial examples is the art of creating a noise that is added to an input signal of a classifying neural network, and thus changing the network's classification, while keeping the noise as tenuous as possible. While the…

Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor trigger into the model at training time. While backdoor…

The incredible effectiveness of adversarial attacks on fooling deep neural networks poses a tremendous hurdle in the widespread adoption of deep learning in safety and security-critical domains. While adversarial defense mechanisms have…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws…

Deep neural networks have significantly improved the performance of face forgery detection models in discriminating Artificial Intelligent Generated Content (AIGC). However, their security is significantly threatened by the injection of…

Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it…

Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this…

While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural…

Training large language models (LLMs) on Python execution traces grounds them in code execution and enables the line-by-line execution prediction of whole Python programs, effectively turning them into neural interpreters (FAIR CodeGen Team…

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Neural networks have proven to be effective at solving machine learning tasks but it is unclear whether they learn any relevant causal relationships, while their black-box nature makes it difficult for modellers to understand and debug…

The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of safeguards against them. This includes attack methods in the…

Inspired by the recent advances in generative models, we introduce a human action generation model in order to generate a consecutive sequence of human motions to formulate novel actions. We propose a framework of an autoencoder and a…

There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towards ending this cycle where we "deflect'' adversarial attacks…