19 accepted papers
Compression techniques such as quantization and low-rank approximation enable large language models (LLMs) to run on current edge hardware with limited computing power, but the key challenge lies in balancing the allocation of precision and low rank within a fixed memory limit. We propose a training
Gradient Boosting Decision Trees (GBDTs) are widely used in industry and academia for their high accuracy and efficiency, particularly on structured data. However, the subject of watermarking GBDT models remains underexplored, especially compared to neural networks. In this work, we present the firs
We present WhisperSplat, the first lossless steganography method for 3D Gaussian Splatting (3DGS) models that hides a full‐resolution 2D image in a single view without any degradation of the model's rendering quality elsewhere. Prior work embeds data by retraining or modifying model weights, alterin…
Generalizable Neural Radiance Fields (GNeRF) are recognized as one of the most promising techniques for novel view synthesis and 3D model generation in real-world applications. However, like other generative models in computer vision, ensuring their adversarial robustness against various threat mode…
Recent research shows that large language models (LLMs) are vulnerable to hijacking attacks under the scenario of in-context learning (ICL) where LLMs demonstrate impressive capabilities in performing tasks by conditioning on a sequence of in-context examples (ICEs) (i.e., prompts with task-specific…
Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that contain evident patterns, rendering remarkable attack effects yet easy detection upon human inspection and defensive algori…
Deep learning intellectual properties (IPs) are high-value assets that are frequently susceptible to theft. This vulnerability has led to significant interest in defending the field's intellectual properties from theft. Recently, watermarking techniques have been extended to protect deep learning ha…
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ black-box attacks to generate such adversarial examples. In t…
Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great importance to study. In contrast to many recent works that exploi…
Recent studies indicate that Vision Transformers (ViTs) are robust against out-of-distribution scenarios. In particular, the Fully Attentional Network (FAN) - a family of ViT backbones, has achieved state-of-the-art robustness. In this paper, we revisit the FAN models and improve their pre-training…
Poisoning attacks are emerging threats to deep neural networks where the adversaries attempt to compromise the models by injecting malicious data points in the clean training data. Poisoning attacks target either the availability or integrity of a model. The availability attack aims to degrade the o…
Along with the evolution of deep neural networks (DNNs) in many real-world applications, the complexity of model building has also dramatically increased. Therefore, it is vital to protect the intellectual property (IP) of the model builder and ensure the trustworthiness of the deployed models. Mean…
This paper presents a framework for embedding watermarks into DNN hardware accelerators. Unlike previous works that have looked at protecting the algorithmic intellectual properties of deep learning systems, this work proposes a methodology for defending deep learning hardware. Our methodology embed…
Adversarial examples have emerged as a severe concern for the security of neural networks. However, the ℓ <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</inf> -distances, typically used as a similarity constraint, often fail to capture human perceive…
In recent years, machine learning models have been shown to be vulnerable to backdoor attacks. Under such attacks, an adversary embeds a stealthy backdoor into the trained model such that the compromised models will behave normally on clean inputs but will misclassify according to the adversary's co…
Recent studies have shown that deep neural networks (DNN) are vulnerable to various adversarial attacks. In particular, an adversary can inject a stealthy backdoor into a model such that the compromised model will behave normally without the presence of the trigger. Techniques for generating backdoo…
Recently, machine learning models have demonstrated to be vulnerable to backdoor attacks, primarily due to the lack of transparency in black-box models such as deep neural networks. A third-party model can be poisoned such that it works adequately in normal conditions but behaves maliciously on samp…
Deep neural networks (DNNs) have become state-of-the-art in many application domains. The increasing complexity and cost for building these models demand means for protecting their intellectual property (IP). This paper presents a novel DNN framework that optimizes the robustness of the embedded wat…
Design of integrated circuits that cannot be reverse engineered is very important for protecting the intellectual property of owners. Integrated circuits can be obfuscated by introducing several modes into the control flow. Only one of the modes is the desired mode and other modes represent either m…