Search Results for author:
Found 11 papers, 3 papers with code
DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
DPAdapter modifies and enhances the sharpness-aware minimization (SAM) technique, utilizing a two-batch strategy to provide a more accurate perturbation estimate and an efficient gradient descent, thereby improving parameter robustness against noise.
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
In the attack, one can construct a PII association task, whereby an LLM is fine-tuned using a minuscule PII dataset, to potentially reinstate and reveal concealed PIIs.
Large Language Model Soft Ideologization via AI-Self-Consciousness
Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks.
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
Finally, we perform both theoretical and experimental analysis, showing that the GRASP enhancement does not reduce the effectiveness of the stealthy attacks against the backdoor detection methods based on weight analysis, as well as other backdoor mitigation methods without using detection.
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data.
Understanding Impacts of Task Similarity on Backdoor Attack and Detection
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect.
PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing
The de novo peptide sequencing, which does not rely on a comprehensive target sequence database, provided us a way to identify novel peptides from tandem mass (MS/MS) spectra.
Bounding The Number of Linear Regions in Local Area for Neural Networks with ReLU Activations
In this paper, we present the first method to estimate the upper bound of the number of linear regions in any sphere in the input space of a given ReLU neural network.
Towards Fair Cross-Domain Adaptation via Generative Learning
Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions.
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
A security threat to deep neural networks (DNN) is backdoor contamination, in which an adversary poisons the training data of a target model to inject a Trojan so that images carrying a specific trigger will always be classified into a specific label.
Cryptography and Security
Understanding Membership Inferences on Well-Generalized Learning Models
Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model.
