Search Results for author:
Found 41 papers, 27 papers with code
DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training
Recent advances in reinforcement learning (RL)-based post-training have led to notable improvements in large language models (LLMs), particularly in enhancing their reasoning capabilities to handle complex tasks.
Scaling Laws in Scientific Discovery with AI and Robot Scientists
Scientific discovery is poised for rapid advancement through advanced robotics and artificial intelligence.
CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
With the rapid advancement of generative AI, it is now possible to synthesize high-quality images in a few seconds.
LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
Large foundation models trained on large-scale visual-text data can significantly enhance Open Vocabulary Object Detection (OVD) through data generation.
Can Large Vision-Language Models Detect Images Copyright Infringement from GenAI?
Our experimental results reveal that LVLMs are prone to overfitting, leading to the misclassification of some negative samples as IP-infringement cases.
ADO: Automatic Data Optimization for Inputs in LLM Prompts
This study explores a novel approach to enhance the performance of Large Language Models (LLMs) through the optimization of input data within prompts.
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
Extensive experiments show that VISTA on average reduces hallucination by abount 40% on evaluated open-ended generation task, and it consistently outperforms existing methods on four benchmarks across four architectures under three decoding strategies.
LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
Visual prompting has gained popularity as a method for adapting pre-trained models to specific tasks, particularly in the realm of parameter-efficient tuning.
MLLM-as-a-Judge for Image Safety without Human Labeling
To address these challenges, we propose a MLLM-based method includes objectifying safety rules, assessing the relevance between rules and images, making quick judgments based on debiased token probabilities with logically complete yet simplified precondition chains for safety rules, and conducting more in-depth reasoning with cascaded chain-of-thought processes if necessary.
Token-Budget-Aware LLM Reasoning
Reasoning is critical for large language models (LLMs) to excel in a wide range of tasks.
Robustness-aware Automatic Prompt Optimization
The performance of Large Language Models (LLMs) is based on the quality of the prompts and the semantic and structural integrity information of the input data.
Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
For Scenario II, based on the reduction strategy from G-Search, we design a parametric sigmoid function (P-Sigmoid) to guide the reduction at each layer of the MLLM, whose parameters are optimized by Bayesian Optimization.
Continuous Concepts Removal in Text-to-image Diffusion Models
Text-to-image diffusion models have shown an impressive ability to generate high-quality images from input textual descriptions.
ProSec: Fortifying Code LLMs with Proactive Security Alignment
Previous work proposes to collect security-focused instruction-tuning dataset from real-world vulnerabilities.
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
In this paper, we introduce SIREN, a novel methodology to proactively trace unauthorized data usage in black-box personalized text-to-image diffusion models.
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, including 10 scenarios (e. g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools, 27 different types of attack/defense methods, and 7 evaluation metrics.
Data-centric NLP Backdoor Defense from the Lens of Memorization
Backdoor attack is a severe threat to the trustworthiness of DNN-based language models.
Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer
Moreover, ECLIPSE is on par with template-based methods in ASR while offering superior attack efficiency, reducing the average attack overhead by 83%.
Visual Agents as Fast and Slow Thinkers
With this novel design, we advocate a flexible system, hierarchical reasoning capabilities, and a transparent decision-making pipeline, all of which contribute to its ability to emulate human-like cognitive processes in visual intelligence.
Ranked #198 on
Visual Question Answering
on MM-Vet
Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output.
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
The StockAgent allows users to evaluate the impact of different external factors on investor trading and to analyze trading behavior and profitability effects.
APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking
Existing automatic prompt engineering algorithms primarily focus on language modeling and classification tasks, leaving the domain of IR, particularly reranking, underexplored.
Evaluating and Mitigating IP Infringement in Visual Generative AI
To mitigate such IP infringement problems, we also propose a defense method against it.
Towards Imperceptible Backdoor Attack in Self-supervised Learning
In this paper, we propose an imperceptible and effective backdoor attack against self-supervised models.
How to Trace Latent Generative Model Generated Images without Artificial Watermark?
To study this problem, we design a latent inversion based method called LatentTracer to trace the generated images of the inspected model by checking if the examined images can be well-reconstructed with an inverted latent input.
Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
In this paper, we explore the hypothesis that LLMs process concepts of varying complexities in different layers, introducing the idea of ``Concept Depth'' to suggest that more complex concepts are typically acquired in deeper layers.
ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction
Specifically, we propose Protein Chain of Thought (ProCoT), which replicates the biological mechanism of signaling pathways as natural language prompts.
Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting.
Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities
Large language models (LLMs) have been applied in many fields and have developed rapidly in recent years.
EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
Nevertheless, they also introduce privacy concerns: firstly, numerous studies underscore the risks to user privacy posed by jailbreaking cloud-based LLMs; secondly, the LLM service providers have access to all user data, which deters individuals from confidently utilizing such services.
Health-LLM: Personalized Retrieval-Augmented Disease Prediction System
Recent advancements in artificial intelligence (AI), especially large language models (LLMs), have significantly advanced healthcare applications and demonstrated potentials in intelligent medical treatment.
DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
To address this issue, we propose a method for detecting such unauthorized data usage by planting the injected memorization into the text-to-image diffusion models trained on the protected dataset.
Alteration-free and Model-agnostic Origin Attribution of Generated Images
To overcome this problem, we first develop an alteration-free and model-agnostic origin attribution method via input reverse-engineering on image generation models, i. e., inverting the input of a particular model for a specific image.
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
Such attacks can be easily affected by retraining on downstream tasks and with different prompting strategies, limiting the transferability of backdoor attacks.
UNICORN: A Unified Backdoor Trigger Inversion Framework
Then, it proposes a unified framework to invert backdoor triggers based on the formalization of triggers and the identified inner behaviors of backdoor models from our analysis.
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.
Rethinking the Reverse-engineering of Trojan Triggers
On average, the detection accuracy of our method is 93\%.
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
Existing attacks use visible patterns (e. g., a patch or image transformations) as triggers, which are vulnerable to human inspection.
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
By further analyzing the training process and model architectures, we found that piece-wise linear functions cause this hyperplane surface.
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.
