Search Results for author:
Found 17 papers, 8 papers with code
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
Backdoor attack poses a significant security threat to Deep Learning applications.
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.
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.
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.
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.
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.
Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense
We develop a novel optimization method for NLPbackdoor inversion.
Better Trigger Inversion Optimization in Backdoor Scanning
A popular trigger inversion method is by optimization.
Complex Backdoor Detection by Symmetric Feature Differencing
Our results on the TrojAI competition rounds 2-4, which have patch backdoors and filter backdoors, show that existing scanners may produce hundreds of false positives (i. e., clean models recognized as trojaned), while our technique removes 78-100% of them with a small increase of false negatives by 0-30%, leading to 17-41% overall accuracy improvement.
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry
A prominent challenge is hence to distinguish natural features and injected backdoors.
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.
PENet: Object Detection using Points Estimation in Aerial Images
Aerial imagery has been increasingly adopted in mission-critical tasks, such as traffic surveillance, smart cities, and disaster assistance.
AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
Due to the inherent robustness of segmentation models, traditional norm-bounded attack methods show limited effect on such type of models.
