SafeGenAi @ NeurIPS 2024

142 papers

Top Research Directions

Research directions most represented by SafeGenAi @ NeurIPS 2024 papers.

Preserving Model Utility During Machine Unlearning 5
The Mechanics of Bias Amplification in Language Models 4
Erasing Memorized Data from Large Language Models 4
The Structural Vulnerability of Language Models to Prompt Injection 3
Machine Unlearning via Targeted Gradient Ascent 2
Efficient Bias Mitigation Without Full Model Retraining 2
Robustness and Reversibility in Machine Unlearning 2
Defending Text to Image Models Against Harmful Generation 2
Visual Grounding and Hallucination in Vision Language Models 2
The Cross Modal Safety Gap in Multimodal Models 2
Factual Inaccuracy and Hallucination in Large Language Models 2
The Mechanics of Backdoor Attacks in Neural Networks 2
Safety Degradation in Fine-Tuned Large Language Models 2
The Vulnerability of Static Defenses to Adaptive Adversaries 2
Reducing the Memory and Latency of Language Model Inference 2

Top Authors

AuthorPapers
Pin-Yu Chen5
Furong Huang4
Reihaneh Rabbany4
Giulio Zizzo3
Kellin Pelrine3
Lei Li3
Miao Xiong3
Tom Goldstein3
Tsung-Yi Ho3
Weitong Zhang3
Xuandong Zhao3
Zora Che3
Aakriti Agrawal2
Adam Golinski2
Alicia Parrish2
Andrea Santilli2
Anirudh Satheesh2
Charvi Rastogi2
Chetan Bansal2
Chinmay Hegde2

Impactful Papers

Papers from SafeGenAi @ NeurIPS 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit
Extracting Unlearned Information from LLMs with Activation Steering
Fair Image Generation from Pre-trained Models by Probabilistic Modeling
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy
Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D Objects
GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
GRE Score: Generative Risk Evaluation for Large Language Models
GuardFormer: Guardrail Instruction Pretraining for Efficient SafeGuarding
Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training
HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment
Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
Hidden in the Noise: Two-Stage Robust Watermarking for Images
How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompt
How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold
How new data pollutes LLM knowledge and how to dilute it
H-Space Sparse Autoencoders
HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere
Identifying and Addressing Delusions for Target-Directed Decision Making
Imitation guided Automated Red Teaming
Inference, Fast and Slow: Reinterpreting VAEs for OOD Detection
Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Integrating Object Detection Modality into Visual Language Model for Enhanced Autonomous Driving Agent
Interactive Semantic Interventions for VLMs: A Human-in-the-Loop Investigation of VLM Failure
INTERPRETABILITY OF LLM DECEPTION: UNIVERSAL MOTIF
INVESTIGATING ANNOTATOR BIAS IN LARGE LANGUAGE MODELS FOR HATE SPEECH DETECTION
Investigating LLM Memorization: Bridging Trojan Detection and Training Data Extraction
Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models
Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review
Jogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
Language Models Can Articulate Their Implicit Goals
Large Language Model Benchmarks Do Not Test Reliability
Lexically-constrained automated prompt augmentation: A case study using adversarial T2I data
LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
Measuring Steerability in Large Language Models
MED: Exploring LLM Memorization of Encrypted Data
miniCodeProps: a Minimal Benchmark for Proving Code Properties
Mitigating Hallucinations in LVLMs via Summary-Guided Decoding
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
Mix Data or Merge Models? Optimizing for Performance and Safety in Multilingual Contexts
Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
Model Manipulation Attacks Enable More Rigorous Evaluations of LLM Capabilities
Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks
MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning
MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds
NMT-Obfuscator Attack: Ignore a sentence in translation with only one word
On a Spurious Interaction between Uncertainty Scores and Answer Evaluation Metrics in Generative QA Tasks

« prev Page 2/3 next »