Search Results for author:
Found 28 papers, 11 papers with code
Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs.
FAKEPCD: Fake Point Cloud Detection via Source Attribution
Take the open-world attribution as an example, FAKEPCD attributes point clouds to known sources with an accuracy of 0. 82-0. 98 and to unknown sources with an accuracy of 0. 73-1. 00.
Comprehensive Assessment of Toxicity in ChatGPT
Moderating offensive, hateful, and toxic language has always been an important but challenging topic in the domain of safe use in NLP.
Prompt Backdoors in Visual Prompt Learning
Specifically, the VPPTaaS provider optimizes a visual prompt given downstream data, and downstream users can use this prompt together with the large pre-trained model for prediction.
Composite Backdoor Attacks Against Large Language Models
Such a Composite Backdoor Attack (CBA) is shown to be stealthier than implanting the same multiple trigger keys in only a single component.
You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
We find that prompt learning achieves around 10\% improvement in the toxicity classification task compared to the baselines, while for the toxic span detection task we find better performance to the best baseline (0. 643 vs. 0. 640 in terms of $F_1$-score).
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
The misuse of large language models (LLMs) has garnered significant attention from the general public and LLM vendors.
Generated Graph Detection
Graph generative models become increasingly effective for data distribution approximation and data augmentation.
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Given the simplicity and effectiveness of the attack method, our study indicates scientific plots indeed constitute a valid side channel for model information stealing attacks.
Backdoor Attacks Against Dataset Distillation
A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset.
Amplifying Membership Exposure via Data Poisoning
In this paper, we investigate the third type of exploitation of data poisoning - increasing the risks of privacy leakage of benign training samples.
Backdoor Attacks in the Supply Chain of Masked Image Modeling
Different from previous work, we are the first to systematically threat modeling on SSL in every phase of the model supply chain, i. e., pre-training, release, and downstream phases.
Cerberus: Exploring Federated Prediction of Security Events
Modern defenses against cyberattacks increasingly rely on proactive approaches, e. g., to predict the adversary's next actions based on past events.
On the Privacy Risks of Cell-Based NAS Architectures
Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance.
Finding MNEMON: Reviving Memories of Node Embeddings
Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks.
Model Stealing Attacks Against Inductive Graph Neural Networks
Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications.
Inference Attacks Against Graph Neural Networks
Second, given a subgraph of interest and the graph embedding, we can determine with high confidence that whether the subgraph is contained in the target graph.
Towards Understanding the Robustness Against Evasion Attack on Categorical Data
Characterizing and assessing the adversarial vulnerability of classification models with categorical input has been a practically important, while rarely explored research problem.
ANDR USPEX : Leveraging Graph Representation Learning to Predict Harmful App Installations on Mobile Devices
Unlike commodity anti-malware solutions on desktop systems, their Android counterparts run as sandboxed applications without root privileges and are limited by Android's permission system.
Graph Representation Learning
Cryptography and Security
Understanding Worldwide Private Information Collection on Android
Mobile phones enable the collection of a wealth of private information, from unique identifiers (e. g., email addresses), to a user's location, to their text messages.
Mobile Security
Cryptography and Security
Node-Level Membership Inference Attacks Against Graph Neural Networks
To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs), has been introduced.
Empowering the Edge Intelligence by Air-Ground Integrated Federated Learning in 6G Networks
Ubiquitous intelligence has been widely recognized as a critical vision of the future sixth generation (6G) networks, which implies the intelligence over the whole network from the core to the edge including end devices.
Networking and Internet Architecture
Gradient Boosting Survival Tree with Applications in Credit Scoring
In order to deal with highly heterogeneous industrial data collected in Chinese market of consumer finance, we propose a nonparametric ensemble tree model called gradient boosting survival tree (GBST) that extends the survival tree models with a gradient boosting algorithm.
ATTACK2VEC: Leveraging Temporal Word Embeddings to Understand the Evolution of Cyberattacks
Despite the fact that cyberattacks are constantly growing in complexity, the research community still lacks effective tools to easily monitor and understand them.
Tiresias: Predicting Security Events Through Deep Learning
With the increased complexity of modern computer attacks, there is a need for defenders not only to detect malicious activity as it happens, but also to predict the specific steps that will be taken by an adversary when performing an attack.
Collaborative and Privacy-Preserving Machine Teaching via Consensus Optimization
To address these challenges, we formulate collaborative teaching as a consensus and privacy-preserving optimization process to minimize teaching risk.
Risk-sensitive Reinforcement Learning
We derive a family of risk-sensitive reinforcement learning methods for agents, who face sequential decision-making tasks in uncertain environments.
Risk-sensitive Markov control processes
We introduce a general framework for measuring risk in the context of Markov control processes with risk maps on general Borel spaces that generalize known concepts of risk measures in mathematical finance, operations research and behavioral economics.
