Search Results for author:
Found 24 papers, 4 papers with code
Benchmarking Bias in Large Language Models during Role-Playing
Our benchmark reveals 72, 716 biased responses across the studied LLMs, with individual models yielding between 7, 754 and 16, 963 biased responses, underscoring the prevalence of bias in role-playing contexts.
A Survey on Physical Adversarial Attacks against Face Recognition Systems
However, a systematic overview focused on physical adversarial attacks against FR systems is still lacking, hindering an in-depth exploration of the challenges and future directions in this field.
Speculative Coreset Selection for Task-Specific Fine-tuning
Task-specific fine-tuning is essential for the deployment of large language models (LLMs), but it requires significant computational resources and time.
Federated Graph Learning with Adaptive Importance-based Sampling
For privacy-preserving graph learning tasks involving distributed graph datasets, federated learning (FL)-based GCN (FedGCN) training is required.
Dormant: Defending against Pose-driven Human Image Animation
Dormant applies protective perturbation to one human image, preserving the visual similarity to the original but resulting in poor-quality video generation.
Perception-guided Jailbreak against Text-to-Image Models
Specifically, we propose identifying a safe phrase that is similar in human perception yet inconsistent in text semantics with the target unsafe word and using it as a substitution.
Compromising Embodied Agents with Contextual Backdoor Attacks
To enable context-dependent behaviors in downstream agents, we implement a dual-modality activation strategy that controls both the generation and execution of program defects through textual and visual triggers.
NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing
In this work, we implement NeuSemSlice, a novel framework that introduces the semantic slicing technique to effectively identify critical neuron-level semantic components in DNN models for semantic-aware model maintenance tasks.
MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling
The core challenge lies in generating smooth and natural transitions between these segments given the inherent complexity and variability of action transitions.
CaBaFL: Asynchronous Federated Learning via Hierarchical Cache and Feature Balance
To address the problem of imbalanced data, the feature balance-guided device selection strategy in CaBaFL adopts the activation distribution as a metric, which enables each intermediate model to be trained across devices with totally balanced data distributions before aggregation.
BadEdit: Backdooring large language models by model editing
It boasts superiority over existing backdoor injection techniques in several areas: (1) Practicality: BadEdit necessitates only a minimal dataset for injection (15 samples).
Purifying Large Language Models by Ensembling a Small Language Model
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources.
Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One
Building on this insight and observation, we develop FairThinking, a pipeline designed to automatically generate roles that enable LLMs to articulate diverse perspectives for fair expressions.
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
To expose this potential vulnerability, we aim to build an adversarial attack forcing SDEdit to generate a specific data distribution aligned with a specified attribute (e. g., female), without changing the input's attribute characteristics.
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
In recent years, LiDAR-camera fusion models have markedly advanced 3D object detection tasks in autonomous driving.
IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks.
FAIRER: Fairness as Decision Rationale Alignment
Existing fairness regularization terms fail to achieve decision rationale alignment because they only constrain last-layer outputs while ignoring intermediate neuron alignment.
On the Robustness of Segment Anything
Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness.
Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing
Machine learning (ML) systems have achieved remarkable performance across a wide area of applications.
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible backdoor attacks.
NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks
Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs.
Unveiling Project-Specific Bias in Neural Code Models
We propose a Cond-Idf measurement to interpret this behavior, which quantifies the relatedness of a token with a label and its project-specificness.
Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
In this paper, we first draw the close connection between adversarial robustness and neuron sensitivities, as sensitive neurons make the most non-trivial contributions to model predictions in the adversarial setting.
Knowledge Consistency between Neural Networks and Beyond
As a generic tool, our method can be broadly used for different applications.
