0

Xingjun Ma

Papers
33

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
33papers

Authored papers

33

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

arXiv 2026

2026

Internal Safety Collapse in Frontier Large Language Models

arXiv 2026

2026

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook

arXiv 2026

2026

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

arXiv 2026

2026

FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

arXiv 2026

2026

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents

arXiv 2026

2026

PixelSmile: Toward Fine-Grained Facial Expression Editing

arXiv 2026

2026

A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5

arXiv 2026

2026

OmniSVG: A Unified Scalable Vector Graphics Generation Model

arXiv 2025

2025

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

arXiv 2025

2025

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

arXiv 2025

2025

WithAnyone: Towards Controllable and ID Consistent Image Generation

arXiv 2025

2025

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models

arXiv 2025

2025

Safety at Scale: A Comprehensive Survey of Large Model Safety

arXiv 2025

2025

Detecting Backdoor Samples in Contrastive Language Image Pretraining

arXiv 2025

2025

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

arXiv 2025

2025

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

arXiv 2024

2024

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks

arXiv 2024

2024

LDReg: Local Dimensionality Regularized Self-Supervised Learning

arXiv 2024

2024

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models

arXiv 2024

2024

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks

CVPR 2025 1

2024

AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

CVPR 2025 1

2024

Fake Alignment: Are LLMs Really Aligned Well?

arXiv 2023

2023

Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models

arXiv 2023

2023

Reconstructive Neuron Pruning for Backdoor Defense

arXiv 2023

2023

Distilling Cognitive Backdoor Patterns within an Image

arXiv 2023

2023

Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

CVPR 2023 1

2022

Few-Shot Backdoor Attacks on Visual Object Tracking

few-shot-backdoor-attacks-on-visual-object

2022

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection

arXiv 2021

2021

Unlearnable Examples: Making Personal Data Unexploitable

unlearnable-examples-making-personal-data

2021

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

NeurIPS 2021 12

2021

Normalized Loss Functions for Deep Learning with Noisy Labels

ICML 2020 1

2020

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

arXiv 2020

2020

Affiliations

No known affiliations.

Frequent co-authors

10

from 33 papers