Search Results for author:
Found 27 papers, 19 papers with code
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
Backdoor attack poses a significant security threat to Deep Learning applications.
InstructEdit: Instruction-based Knowledge Editing for Large Language Models
Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance.
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing
Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs).
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities.
A Comprehensive Study of Knowledge Editing for Large Language Models
In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
Ranked #1 on
knowledge editing
on zsRE
(using extra training data)
Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs
Instead, it exploits the fact that even when an LLM rejects a toxic request, a harmful response often hides deep in the output logits.
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training.
Can We Edit Multimodal Large Language Models?
In this paper, we focus on editing Multimodal Large Language Models (MLLMs).
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data.
Editing Large Language Models: Problems, Methods, and Opportunities
Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context.
Detecting Backdoors in Pre-trained Encoders
We show the effectiveness of our method on image encoders pre-trained on ImageNet and OpenAI's CLIP 400 million image-text pairs.
Editing Language Model-based Knowledge Graph Embeddings
To address this issue, we propose a new task of editing language model-based KG embeddings in this paper.
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks.
MEDIC: Remove Model Backdoors via Importance Driven Cloning
It trains the clone model from scratch on a very small subset of samples and aims to minimize a cloning loss that denotes the differences between the activations of important neurons across the two models.
Backdoor Vulnerabilities in Normally Trained Deep Learning Models
We leverage 20 different types of injected backdoor attacks in the literature as the guidance and study their correspondences in normally trained models, which we call natural backdoor vulnerabilities.
RITA: Boost Driving Simulators with Realistic Interactive Traffic Flow
High-quality traffic flow generation is the core module in building simulators for autonomous driving.
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting.
DECK: Model Hardening for Defending Pervasive Backdoors
As such, using the samples derived from our attack in adversarial training can harden a model against these backdoor vulnerabilities.
Multi-modal Protein Knowledge Graph Construction and Applications
Existing data-centric methods for protein science generally cannot sufficiently capture and leverage biology knowledge, which may be crucial for many protein tasks.
Relphormer: Relational Graph Transformer for Knowledge Graph Representations
To this end, we propose a new variant of Transformer for knowledge graph representations dubbed Relphormer.
Ranked #3 on
Link Prediction
on FB15k-237
Contrastive Demonstration Tuning for Pre-trained Language Models
Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios.
A spectral-spatial fusion anomaly detection method for hyperspectral imagery
In hyperspectral, high-quality spectral signals convey subtle spectral differences to distinguish similar materials, thereby providing unique advantage for anomaly detection.
OntoProtein: Protein Pretraining With Gene Ontology Embedding
We construct a novel large-scale knowledge graph that consists of GO and its related proteins, and gene annotation texts or protein sequences describe all nodes in the graph.
Learning to Filter: Siamese Relation Network for Robust Tracking
RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result.
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
By iteratively and stochastically selecting the most promising labels for optimization with the guidance of an objective function, we substantially reduce the complexity, allowing to handle models with many classes.
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data.
Towards Feature Space Adversarial Attack
We propose a new adversarial attack to Deep Neural Networks for image classification.
