Search Results for author:
Found 14 papers, 10 papers with code
Exploring Backdoor Vulnerabilities of Chat Models
Chat models are extensively adopted across various real-world scenarios, thus the security of chat models deserves increasing attention.
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
We first formulate a general framework of agent backdoor attacks, then we present a thorough analysis on the different forms of agent backdoor attacks.
Enabling Large Language Models to Learn from Rules
The current knowledge learning paradigm of LLMs is mainly based on learning from examples, in which LLMs learn the internal rule implicitly from a certain number of supervised examples.
Two Stream Scene Understanding on Graph Embedding
This architecture utilizes a graph feature stream and an image feature stream, aiming to merge the strengths of both modalities for improved performance in image classification and scene graph generation tasks.
Towards Codable Watermarking for Injecting Multi-bits Information to LLMs
As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs.
Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter
However, as pre-trained language models (PLMs) continue to increase in size, the communication cost for transmitting parameters during synchronization has become a training speed bottleneck.
Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features
We find that: (1) no existing method behaves well in both settings; (2) fine-tuning PLMs on in-distribution data benefits detecting semantic shifts but severely deteriorates detecting non-semantic shifts, which can be attributed to the distortion of task-agnostic features.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning
Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner.
When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning
Federated Learning has become a widely-used framework which allows learning a global model on decentralized local datasets under the condition of protecting local data privacy.
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
In this work, we take the first step to investigate the unconcealment of textual poisoned samples at the intermediate-feature level and propose a feature-based efficient online defense method.
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
Motivated by this observation, we construct a word-based robustness-aware perturbation to distinguish poisoned samples from clean samples to defend against the backdoor attacks on natural language processing (NLP) models.
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundary.
Rethinking Stealthiness of Backdoor Attack against NLP Models
In this work, we point out a potential problem of current backdoor attacking research: its evaluation ignores the stealthiness of backdoor attacks, and most of existing backdoor attacking methods are not stealthy either to system deployers or to system users.
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples.
