Copertina

ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kang, Hankun, Miao, Xin, Chen, Jianhao, Wen, Jintao, Xu, Mayi, Zhang, Weiyu, Lu, Wenpeng, Qian, Tieyun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Toxicity Detection towards Adaptability to Changing Perturbations
di: Kang, Hankun, et al.
Pubblicazione: (2024)

Aligning VLM Assistants with Personalized Situated Cognition
di: Li, Yongqi, et al.
Pubblicazione: (2025)

Reasoning based on symbolic and parametric knowledge bases: a survey
di: Xu, Mayi, et al.
Pubblicazione: (2025)

Prompting Large Language Models for Counterfactual Generation: An Empirical Study
di: Li, Yongqi, et al.
Pubblicazione: (2023)

A Survey on Training-free Alignment of Large Language Models
di: Pan, Birong, et al.
Pubblicazione: (2025)

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations
di: Li, Xiaohu, et al.
Pubblicazione: (2025)

Enhancing Relation Extraction via Supervised Rationale Verification and Feedback
di: Li, Yongqi, et al.
Pubblicazione: (2024)

Can a Small Model Learn to Look Before It Leaps? Dynamic Learning and Proactive Correction for Hallucination Detection
di: Bao, Zepeng, et al.
Pubblicazione: (2025)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
di: Pan, Birong, et al.
Pubblicazione: (2025)

Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answering
di: Ning, Yunfeng, et al.
Pubblicazione: (2025)

RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
di: Chen, Jianhao, et al.
Pubblicazione: (2025)

Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models
di: Pi, Qiankun, et al.
Pubblicazione: (2026)

Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
di: Liu, Jiacheng, et al.
Pubblicazione: (2025)

Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
di: Chen, Jianhao, et al.
Pubblicazione: (2026)

AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models
di: Kang, Hankun, et al.
Pubblicazione: (2026)

KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing
di: Xu, Zhenhua, et al.
Pubblicazione: (2026)

Conti-Fuse: A Novel Continuous Decomposition-based Fusion Framework for Infrared and Visible Images
di: Li, Hui, et al.
Pubblicazione: (2024)

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
di: Xu, Wenpeng
Pubblicazione: (2026)

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling
di: Chen, Yuqi, et al.
Pubblicazione: (2024)

Knowledge Graph Tokenization for Behavior-Aware Generative Next POI Recommendation
di: Sun, Ke, et al.
Pubblicazione: (2025)

In-Application Defense Against Evasive Web Scans through Behavioral Analysis
di: Ousat, Behzad, et al.
Pubblicazione: (2024)

Michelangelo / Giulio Carlo Argan, Bruno Conti
di: Argan, Giulio C
Pubblicazione: (1987)

The Protective Role of Ambient Ultraviolet Radiation Against Dementia: An Ecological Analysis of Global Data
di: Wenpeng You
Pubblicazione: (2025)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
di: Li, Siyuan, et al.
Pubblicazione: (2026)

Guardians of the Network: An Ensemble Learning Framework With Adversarial Alignment for Evasive Cyber Threat Detection
di: Khandakar Md Shafin, et al.
Pubblicazione: (2025)

Local development and competitiveness / Sergio Conti ; Paolo Giaccaria
di: Conti, Sergio

EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection
di: Zhu, Chenyang, et al.
Pubblicazione: (2026)

Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
di: Kim, San, et al.
Pubblicazione: (2024)

Adversarial Pre-Padding: Generating Evasive Network Traffic Against Transformer-Based Classifiers
di: Jing, Quanliang, et al.
Pubblicazione: (2025)

EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
di: Xu, Ancheng, et al.
Pubblicazione: (2025)

POSTER: A Multi-Signal Model for Detecting Evasive Smishing
di: Hosseinpour, Shaghayegh, et al.
Pubblicazione: (2025)

Variety Evasive Subspace Families
di: Guo, Zeyu
Pubblicazione: (2021)

A Unified and Scalable Algorithm Framework of User-Defined Temporal $(k,\mathcal{X})$-Core Query
di: Zhong, Ming, et al.
Pubblicazione: (2023)

Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions
di: Li, Yongqi, et al.
Pubblicazione: (2026)

Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
di: Gong, Xueluan, et al.
Pubblicazione: (2024)

Evasive Random Walks and the Clairvoyant Demon
di: Abrams, Aaron, et al.
Pubblicazione: (2025)

SmoothGuard: Defending Multimodal Large Language Models with Noise Perturbation and Clustering Aggregation
di: Su, Guangzhi, et al.
Pubblicazione: (2025)

RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection
di: Zhu, He, et al.
Pubblicazione: (2026)

Guarding Terrains with Guards on a Line
di: Kang, Byeonguk, et al.
Pubblicazione: (2025)

Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
di: Qiu, Haomiao, et al.
Pubblicazione: (2025)