Search Results for author:
Found 15 papers, 7 papers with code
Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
While large language models have demonstrated exceptional performance across a wide range of tasks, they remain susceptible to hallucinations -- generating plausible yet factually incorrect contents.
TruthFlow: Truthful LLM Generation via Representation Flow Correction
Large language models (LLMs) are known to struggle with consistently generating truthful responses.
Data Free Backdoor Attacks
Existing backdoor attacks require either retraining the classifier with some clean data or modifying the model's architecture.
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation of Not Safe for Work (NSFW) content.
On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
Our findings are verified in: (1) the scenario of multi-round question answering, by comprehensively demonstrating that intrinsic self-correction can progressively introduce performance gains through iterative interactions, ultimately converging to stable performance; and (2) the context of intrinsic self-correction for enhanced morality, in which we provide empirical evidence that iteratively applying instructions reduces model uncertainty towards convergence, which then leads to convergence of both the calibration error and self-correction performance, ultimately resulting in a stable state of intrinsic self-correction.
XPrompt:Explaining Large Language Model's Generation via Joint Prompt Attribution
In this study, we introduce a counterfactual explanation framework based on joint prompt attribution, XPrompt, which aims to explain how a few prompt texts collaboratively influences the LLM's complete generation.
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications.
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace.
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers.
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
In this work, we show that it is possible to conduct stealthy and persistent unalignment on large language models via backdoor injections.
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
IMPRESS is based on the key observation that imperceptible perturbations could lead to a perceptible inconsistency between the original image and the diffusion-reconstructed image, which can be used to devise a new optimization strategy for purifying the image, which may weaken the protection of the original image from unauthorized data usage (e. g., style mimicking, malicious editing).
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?
A natural question is "could alignment really prevent those open-sourced large language models from being misused to generate undesired content?''.
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
In this work, we introduce a Robustly Aligned LLM (RA-LLM) to defend against potential alignment-breaking attacks.
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
Temporal shifts -- distribution shifts arising from the passage of time -- often occur gradually and have the additional structure of timestamp metadata.
OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning
Utilizing OmniLytics, many distributed data owners can contribute their private data to collectively train an ML model requested by some model owners, and receive compensation for data contribution.
