Copertina

APEX: Probing Neural Networks via Activation Perturbation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ren, Tao, Luo, Xiaoyu, Li, Qiongxiu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Byzantine-Resilient Federated Learning via Distributed Optimization
di: Xia, Yufei, et al.
Pubblicazione: (2025)

Probing Graph Neural Network Activation Patterns Through Graph Topology
di: Tori, Floriano, et al.
Pubblicazione: (2026)

APEX-Agents
di: Vidgen, Bertie, et al.
Pubblicazione: (2026)

Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation
di: Choi, Yoonhyuk, et al.
Pubblicazione: (2022)

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
di: Li, Yibo, et al.
Pubblicazione: (2026)

DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization
di: Luo, Xiaoyu, et al.
Pubblicazione: (2024)

Probing the Embedding Space of Transformers via Minimal Token Perturbations
di: Conti, Eddie, et al.
Pubblicazione: (2025)

Unifying Adversarial Perturbation for Graph Neural Networks
di: Yang, Jinluan, et al.
Pubblicazione: (2025)

Propositional Logic for Probing Generalization in Neural Networks
di: Langedijk, Anna, et al.
Pubblicazione: (2025)

Ray-Tracing for Conditionally Activated Neural Networks
di: Gallicchio, Claudio, et al.
Pubblicazione: (2025)

Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks
di: Eilers, Florian, et al.
Pubblicazione: (2026)

Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphs
di: He, Shuqi, et al.
Pubblicazione: (2024)

Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
di: Li, Xiaoyu, et al.
Pubblicazione: (2025)

Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
di: Yu, Wenrui, et al.
Pubblicazione: (2024)

LLM Unlearning via Neural Activation Redirection
di: Shen, William F., et al.
Pubblicazione: (2025)

Learning from Historical Activations in Graph Neural Networks
di: Galron, Yaniv, et al.
Pubblicazione: (2026)

Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations
di: González-Santana, Alejandro J., et al.
Pubblicazione: (2026)

Efficient Neural Networks with Discrete Cosine Transform Activations
di: Martinez-Gost, Marc, et al.
Pubblicazione: (2025)

Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verification
di: Marzari, Luca, et al.
Pubblicazione: (2025)

Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Effective Loss Landscapes via the Fokker--Planck Equation
di: Yin, Shuyu, et al.
Pubblicazione: (2024)

CFNN: Continued Fraction Neural Network
di: Wang, Chao, et al.
Pubblicazione: (2026)

APEX$^2$: Adaptive and Extreme Summarization for Personalized Knowledge Graphs
di: Li, Zihao, et al.
Pubblicazione: (2024)

Probe-Free Low-Rank Activation Intervention
di: Jiang, Chonghe, et al.
Pubblicazione: (2025)

Microsaccade-Inspired Probing: Positional Encoding Perturbations Reveal LLM Misbehaviours
di: Melo, Rui, et al.
Pubblicazione: (2025)

Red-teaming Activation Probes using Prompted LLMs
di: Blandfort, Phil, et al.
Pubblicazione: (2025)

Learning Dynamics of Deep Learning -- Force Analysis of Deep Neural Networks
di: Ren, Yi
Pubblicazione: (2025)

ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs
di: Maheri, Mohammad M, et al.
Pubblicazione: (2025)

GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition
di: Deng, Hao, et al.
Pubblicazione: (2026)

Volatility in Certainty (VC): A Metric for Detecting Adversarial Perturbations During Inference in Neural Network Classifiers
di: Hemmati, Vahid, et al.
Pubblicazione: (2025)

Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability
di: Bini, Lorenzo, et al.
Pubblicazione: (2024)

Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations
di: Joudaki, Amir, et al.
Pubblicazione: (2024)

Developing Training Procedures for Piecewise-linear Spline Activation Functions in Neural Networks
di: Patty, William H
Pubblicazione: (2025)

Explaining Time Series via Contrastive and Locally Sparse Perturbations
di: Liu, Zichuan, et al.
Pubblicazione: (2024)

Visualizing Neural Network Imagination
di: Wichers, Nevan, et al.
Pubblicazione: (2024)

From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges
di: Li, Qiongxiu, et al.
Pubblicazione: (2025)

Factor Graph-based Interpretable Neural Networks
di: Li, Yicong, et al.
Pubblicazione: (2025)

Exploration by Random Reward Perturbation
di: Ma, Haozhe, et al.
Pubblicazione: (2025)

Tensor-view Topological Graph Neural Network
di: Wen, Tao, et al.
Pubblicazione: (2024)

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
di: Sartor, Davide, et al.
Pubblicazione: (2025)

Probing Neural Combinatorial Optimization Models
di: Zhang, Zhiqin, et al.
Pubblicazione: (2025)