2 citations · 3 across the 9 of their papers we have counts for
9 papers
CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs
Zhengxing Li, David J. Miller, Guangmingmei Yang +1
While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such methods for LLMs. First, the LLM i…
A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization
Guangmingmei Yang, David J. Miller, George Kesidis
Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks and backdoors (Trojans). In…
Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
Guangmingmei Yang, David J. Miller, George Kesidis
Most post-training backdoor detection methods rely on attacked models exhibiting extreme outlier detection statistics for the target class of an attack, compared to non-target clas…
Inverting Trojans in LLMs
Zhengxing Li, Guangmingmei Yang, Jayaram Raghuram +2
While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM i…
A Study of Backdoors in Instruction Fine-tuned Language Models
Jayaram Raghuram, George Kesidis, David J. Miller
Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction),…
CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors
Guangmingmei Yang, Xi Li, Hang Wang +2
A variety of defenses have been proposed against Trojans planted in (backdoor attacks on) deep neural network (DNN) classifiers. Backdoor-agnostic methods seek to reliably detect a…
Post-Training Overfitting Mitigation in DNN Classifiers
Hang Wang, David J. Miller, George Kesidis
Well-known (non-malicious) sources of overfitting in deep neural net (DNN) classifiers include: i) large class imbalances; ii) insufficient training-set diversity; and iii) over-tr…
Backdoor Mitigation by Correcting the Distribution of Neural Activations
Xi Li, Zhen Xiang, David J. Miller +1
Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target clas…
Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection
Hang Wang, Zhen Xiang, David J. Miller +1
Deep neural networks are vulnerable to backdoor attacks (Trojans), where an attacker poisons the training set with backdoor triggers so that the neural network learns to classify t…