Search Results for author:
Found 15 papers, 6 papers with code
Flatness-aware Sequential Learning Generates Resilient Backdoors
Based on this finding, we re-formulate backdoor training through the lens of CL and propose a novel framework, named Sequential Backdoor Learning (SBL), that can generate resilient backdoors.
Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text.
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
We study different strategies for selectively poisoning a small set of training samples in the target class to boost the attack success rate in this setting.
MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs
The rapid progress in machine learning (ML) has brought forth many large language models (LLMs) that excel in various tasks and areas.
Forget but Recall: Incremental Latent Rectification in Continual Learning
Intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs).
Fooling the Textual Fooler via Randomizing Latent Representations
Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave.
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
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.
Ranked #1 on
Image Classification
on delete
Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack
The vulnerabilities to backdoor attacks have recently threatened the trustworthiness of machine learning models in practical applications.
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class
To achieve this goal, we propose to represent the trigger function as a class-conditional generative model and to inject the backdoor in a constrained optimization framework, where the trigger function learns to generate an optimal trigger pattern to attack any target class at will while simultaneously embedding this generative backdoor into the trained model.
CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing
Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data.
Defending Backdoor Attacks on Vision Transformer via Patch Processing
We first examine the vulnerability of ViTs against various backdoor attacks and find that ViTs are also quite vulnerable to existing attacks.
One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching
However, in the existing deep supervised hashing methods, coding balance and low-quantization error are difficult to achieve and involve several losses.
Under-confidence Backdoors Are Resilient and Stealthy Backdoors
In order to achieve a high attack success rate using as few poisoned training samples as possible, most existing attack methods change the labels of the poisoned samples to the target class.
Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space
We use the intuition that it is much better to train the GAN generator by minimizing the distributional distance between real and generated images in a small dimensional feature space representing such a manifold than on the original pixel-space.
Image Hashing by Minimizing Discrete Component-wise Wasserstein Distance
In this paper, we show that the high sample-complexity requirement often results in sub-optimal retrieval performance of the adversarial hashing methods.
