Suchergebnisse: Verfasser :: Library Catalog

1

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks Autoría: Liu, Zesen, Cong, Tianshuo, He, Xinlei, Li, Qi

Veröffentlicht 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
2

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers Autoría: Zheng, Jingyi, Hu, Tianyi, Cong, Tianshuo, He, Xinlei

Veröffentlicht 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
3

Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models Autoría: Yi, Sibo, Cong, Tianshuo, He, Xinlei, Li, Qi, Song, Jiaxing

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
4

Watermarking LLM-Generated Datasets in Downstream Tasks Autoría: Liu, Yugeng, Cong, Tianshuo, Backes, Michael, Li, Zheng, Zhang, Yang

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
5

Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models Autoría: Liu, Yugeng, Cong, Tianshuo, Zhao, Zhengyu, Backes, Michael, Shen, Yun, Zhang, Yang

Veröffentlicht 2023

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
6

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning Autoría: Zhang, Heyi, Liu, Yule, He, Xinlei, Wu, Jun, Cong, Tianshuo, Huang, Xinyi

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
7

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models Autoría: Ran, Delong, He, Xinlei, Cong, Tianshuo, Wang, Anyu, Li, Qi, Wang, Xiaoyun

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
8

Cryptanalysis of Pseudorandom Error-Correcting Codes Autoría: Wang, Tianrui, Wang, Anyu, Cong, Tianshuo, Ran, Delong, Liu, Jinyuan, Wang, Xiaoyun

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
9

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models Autoría: Ran, Delong, Liu, Jinyuan, Gong, Yichen, Zheng, Jingyi, He, Xinlei, Cong, Tianshuo, Wang, Anyu

Veröffentlicht 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
10

From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses Autoría: Meng, Xiangtao, Cong, Tianshuo, Wang, Li, Chen, Wenyu, Li, Zheng, Guo, Shanqing, Wang, Xiaoyun

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
11

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis Autoría: Song, Da, Huang, Yuheng, Chen, Boqi, Cong, Tianshuo, Goebel, Randy, Ma, Lei, Khomh, Foutse

Veröffentlicht 2026

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
12

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts Autoría: Gong, Yichen, Ran, Delong, Liu, Jinyuan, Wang, Conglei, Cong, Tianshuo, Wang, Anyu, Duan, Sisi, Wang, Xiaoyun

Veröffentlicht 2023

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
13

Jailbreak Attacks and Defenses Against Large Language Models: A Survey Autoría: Yi, Sibo, Liu, Yule, Sun, Zhen, Cong, Tianshuo, He, Xinlei, Song, Jiaxing, Xu, Ke, Li, Qi

Veröffentlicht 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
14

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning Autoría: Sun, Zhen, Cong, Tianshuo, Liu, Yule, Lin, Chenhao, He, Xinlei, Chen, Rongmao, Han, Xingshuo, Huang, Xinyi

Veröffentlicht 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
15

Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging Autoría: Cong, Tianshuo, Ran, Delong, Liu, Zesen, He, Xinlei, Liu, Jinyuan, Gong, Yichen, Li, Qi, Wang, Anyu, Wang, Xiaoyun

Veröffentlicht 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
16

Auditing Data Membership in Reinforcement Learning With Verifiable Rewards Autoría: Liu, Yule, Zhang, Heyi, Zheng, Jinyi, Sun, Zhen, Peng, Zifan, Wei, Jiaheng, Cong, Tianshuo, Yang, Yilong, He, Xinlei

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:
17

Can VLMs Detect and Localize Fine-Grained AI-Edited Images? Autoría: Sun, Zhen, Zhang, Ziyi, Luo, Zeren, Zhong, Zhiyuan, Sha, Zeyang, Cong, Tianshuo, Li, Zheng, Cui, Shiwen, Wang, Weiqiang, Wei, Jiaheng, He, Xinlei, Li, Qi, Wang, Qian

Veröffentlicht 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Datensatz separat aufrufen
Zu den Favoriten

Gespeichert in:

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks Autoría: Liu, Zesen, Cong, Tianshuo, He, Xinlei, Li, Qi

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers Autoría: Zheng, Jingyi, Hu, Tianyi, Cong, Tianshuo, He, Xinlei

Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models Autoría: Yi, Sibo, Cong, Tianshuo, He, Xinlei, Li, Qi, Song, Jiaxing

Watermarking LLM-Generated Datasets in Downstream Tasks Autoría: Liu, Yugeng, Cong, Tianshuo, Backes, Michael, Li, Zheng, Zhang, Yang

Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models Autoría: Liu, Yugeng, Cong, Tianshuo, Zhao, Zhengyu, Backes, Michael, Shen, Yun, Zhang, Yang

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning Autoría: Zhang, Heyi, Liu, Yule, He, Xinlei, Wu, Jun, Cong, Tianshuo, Huang, Xinyi

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models Autoría: Ran, Delong, He, Xinlei, Cong, Tianshuo, Wang, Anyu, Li, Qi, Wang, Xiaoyun

Cryptanalysis of Pseudorandom Error-Correcting Codes Autoría: Wang, Tianrui, Wang, Anyu, Cong, Tianshuo, Ran, Delong, Liu, Jinyuan, Wang, Xiaoyun

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models Autoría: Ran, Delong, Liu, Jinyuan, Gong, Yichen, Zheng, Jingyi, He, Xinlei, Cong, Tianshuo, Wang, Anyu

From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses Autoría: Meng, Xiangtao, Cong, Tianshuo, Wang, Li, Chen, Wenyu, Li, Zheng, Guo, Shanqing, Wang, Xiaoyun

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis Autoría: Song, Da, Huang, Yuheng, Chen, Boqi, Cong, Tianshuo, Goebel, Randy, Ma, Lei, Khomh, Foutse

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts Autoría: Gong, Yichen, Ran, Delong, Liu, Jinyuan, Wang, Conglei, Cong, Tianshuo, Wang, Anyu, Duan, Sisi, Wang, Xiaoyun

Jailbreak Attacks and Defenses Against Large Language Models: A Survey Autoría: Yi, Sibo, Liu, Yule, Sun, Zhen, Cong, Tianshuo, He, Xinlei, Song, Jiaxing, Xu, Ke, Li, Qi

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning Autoría: Sun, Zhen, Cong, Tianshuo, Liu, Yule, Lin, Chenhao, He, Xinlei, Chen, Rongmao, Han, Xingshuo, Huang, Xinyi

Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging Autoría: Cong, Tianshuo, Ran, Delong, Liu, Zesen, He, Xinlei, Liu, Jinyuan, Gong, Yichen, Li, Qi, Wang, Anyu, Wang, Xiaoyun

Auditing Data Membership in Reinforcement Learning With Verifiable Rewards Autoría: Liu, Yule, Zhang, Heyi, Zheng, Jinyi, Sun, Zhen, Peng, Zifan, Wei, Jiaheng, Cong, Tianshuo, Yang, Yilong, He, Xinlei

Can VLMs Detect and Localize Fine-Grained AI-Edited Images? Autoría: Sun, Zhen, Zhang, Ziyi, Luo, Zeren, Zhong, Zhiyuan, Sha, Zeyang, Cong, Tianshuo, Li, Zheng, Cui, Shiwen, Wang, Weiqiang, Wei, Jiaheng, He, Xinlei, Li, Qi, Wang, Qian

Suchergebnisse - Cong, Tianshuo

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks Autoría: Liu, Zesen, Cong, Tianshuo, He, Xinlei, Li, Qi

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers Autoría: Zheng, Jingyi, Hu, Tianyi, Cong, Tianshuo, He, Xinlei

Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models Autoría: Yi, Sibo, Cong, Tianshuo, He, Xinlei, Li, Qi, Song, Jiaxing

Watermarking LLM-Generated Datasets in Downstream Tasks Autoría: Liu, Yugeng, Cong, Tianshuo, Backes, Michael, Li, Zheng, Zhang, Yang

Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models Autoría: Liu, Yugeng, Cong, Tianshuo, Zhao, Zhengyu, Backes, Michael, Shen, Yun, Zhang, Yang

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning Autoría: Zhang, Heyi, Liu, Yule, He, Xinlei, Wu, Jun, Cong, Tianshuo, Huang, Xinyi

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models Autoría: Ran, Delong, He, Xinlei, Cong, Tianshuo, Wang, Anyu, Li, Qi, Wang, Xiaoyun

Cryptanalysis of Pseudorandom Error-Correcting Codes Autoría: Wang, Tianrui, Wang, Anyu, Cong, Tianshuo, Ran, Delong, Liu, Jinyuan, Wang, Xiaoyun

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models Autoría: Ran, Delong, Liu, Jinyuan, Gong, Yichen, Zheng, Jingyi, He, Xinlei, Cong, Tianshuo, Wang, Anyu

From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses Autoría: Meng, Xiangtao, Cong, Tianshuo, Wang, Li, Chen, Wenyu, Li, Zheng, Guo, Shanqing, Wang, Xiaoyun

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis Autoría: Song, Da, Huang, Yuheng, Chen, Boqi, Cong, Tianshuo, Goebel, Randy, Ma, Lei, Khomh, Foutse

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts Autoría: Gong, Yichen, Ran, Delong, Liu, Jinyuan, Wang, Conglei, Cong, Tianshuo, Wang, Anyu, Duan, Sisi, Wang, Xiaoyun

Jailbreak Attacks and Defenses Against Large Language Models: A Survey Autoría: Yi, Sibo, Liu, Yule, Sun, Zhen, Cong, Tianshuo, He, Xinlei, Song, Jiaxing, Xu, Ke, Li, Qi

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning Autoría: Sun, Zhen, Cong, Tianshuo, Liu, Yule, Lin, Chenhao, He, Xinlei, Chen, Rongmao, Han, Xingshuo, Huang, Xinyi

Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging Autoría: Cong, Tianshuo, Ran, Delong, Liu, Zesen, He, Xinlei, Liu, Jinyuan, Gong, Yichen, Li, Qi, Wang, Anyu, Wang, Xiaoyun

Auditing Data Membership in Reinforcement Learning With Verifiable Rewards Autoría: Liu, Yule, Zhang, Heyi, Zheng, Jinyi, Sun, Zhen, Peng, Zifan, Wei, Jiaheng, Cong, Tianshuo, Yang, Yilong, He, Xinlei

Can VLMs Detect and Localize Fine-Grained AI-Edited Images? Autoría: Sun, Zhen, Zhang, Ziyi, Luo, Zeren, Zhong, Zhiyuan, Sha, Zeyang, Cong, Tianshuo, Li, Zheng, Cui, Shiwen, Wang, Weiqiang, Wei, Jiaheng, He, Xinlei, Li, Qi, Wang, Qian

Suchwerkzeuge: