Related papers: Manipulating Neural Path Planners via Slight Pertu…

The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones. In this paper, we propose a novel backdoor…

Neural networks have demonstrated a wide range of successes, but their ``black box" nature raises concerns about transparency and reliability. Previous research on ReLU networks has sought to unwrap these networks into linear models based…

Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A…

Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target class whenever the attacker's backdoor trigger is present. In…

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…

The following work presents how autoencoding all the possible hidden activations of a network for a given problem can provide insight about its structure, behavior, and vulnerabilities. The method, termed self-introspection, can show that a…

Precise future human motion prediction over sub-second horizons from past observations is crucial for various safety-critical applications. To date, only a few studies have examined the vulnerability of skeleton-based neural networks to…

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…

Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…

Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated,…

For saving cost, many deep neural networks (DNNs) are trained on third-party datasets downloaded from internet, which enables attacker to implant backdoor into DNNs. In 2D domain, inherent structures of different image formats are similar.…

Navigating mobile robots through environments shared with humans is challenging. From the perspective of the robot, humans are dynamic obstacles that must be avoided. These obstacles make the collision-free space nonconvex, which leads to…

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely. In practice, models are…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Speech recognition systems driven by DNNs have revolutionized human-computer interaction through voice interfaces, which significantly facilitate our daily lives. However, the growing popularity of these systems also raises special concerns…

Federated learning has seen increased adoption in recent years in response to the growing regulatory demand for data privacy. However, the opaque local training process of federated learning also sparks rising concerns about model…

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor attack is the most cunning one and can occur in almost…

We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during…