Copertina

Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dankworth, Raik, Schwalbe, Gesina
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Power side-channel leakage localization through adversarial training of deep neural networks
di: Gammell, Jimmy, et al.
Pubblicazione: (2024)

Can sparsity improve the privacy of neural networks?
di: Gonon, Antoine, et al.
Pubblicazione: (2023)

ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
di: Clifford, Eleanor, et al.
Pubblicazione: (2022)

AttackLLM: LLM-based Attack Pattern Generation for an Industrial Control System
di: Ahmed, Chuadhry Mujeeb
Pubblicazione: (2025)

Towards Efficient Machine Learning Method for IoT DDoS Attack Detection
di: Modi, P
Pubblicazione: (2024)

Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning
di: Jiang, Yu, et al.
Pubblicazione: (2024)

Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
di: Giri, Nandakrishna, et al.
Pubblicazione: (2026)

In-network Attack Detection with Federated Deep Learning in IoT Networks: Real Implementation and Analysis
di: Chaudhary, Devashish, et al.
Pubblicazione: (2026)

SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
di: Xu, Haotian, et al.
Pubblicazione: (2025)

Towards Automatic Hands-on-Keyboard Attack Detection Using LLMs in EDR Solutions
di: Portnoy, Amit, et al.
Pubblicazione: (2024)

LFFR: Logistic Function For (single-output) Regression
di: Chiang, John
Pubblicazione: (2024)

Sybil-based Virtual Data Poisoning Attacks in Federated Learning
di: Zhu, Changxun, et al.
Pubblicazione: (2025)

FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs
di: Meerza, Syed Irfan Ali, et al.
Pubblicazione: (2026)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
di: Gao, Yue, et al.
Pubblicazione: (2023)

Sparsity in neural networks can improve their privacy
di: Gonon, Antoine, et al.
Pubblicazione: (2023)

Using Graph Theory for Improving Machine Learning-based Detection of Cyber Attacks
di: Zonneveld, Giacomo, et al.
Pubblicazione: (2024)

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning
di: Wang, Yujing, et al.
Pubblicazione: (2024)

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
di: Pham, Dzung, et al.
Pubblicazione: (2023)

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
di: Guo, Ji, et al.
Pubblicazione: (2026)

FedRecAttack: Model Poisoning Attack to Federated Recommendation
di: Rong, Dazhong, et al.
Pubblicazione: (2022)

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
di: Jin, Zhibo, et al.
Pubblicazione: (2024)

CST-AFNet: A dual attention-based deep learning framework for intrusion detection in IoT networks
di: Ishtiaq, Waqas, et al.
Pubblicazione: (2025)

Attack Smarter: Attention-Driven Fine-Grained Webpage Fingerprinting Attacks
di: Yuan, Yali, et al.
Pubblicazione: (2025)

Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
di: Obadinma, Stephen, et al.
Pubblicazione: (2024)

Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks
di: Zhang, Jiahao, et al.
Pubblicazione: (2026)

Attack and Defense of Deep Learning Models in the Field of Web Attack Detection
di: Shi, Lijia, et al.
Pubblicazione: (2024)

CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
di: Mu, Fangwen, et al.
Pubblicazione: (2024)

Non-omniscient backdoor injection with one poison sample: Proving the one-poison hypothesis for linear regression, linear classification, and 2-layer ReLU neural networks
di: Peinemann, Thorsten, et al.
Pubblicazione: (2025)

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
di: Yao, Yuan, et al.
Pubblicazione: (2025)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
di: Zhan, Qiusi, et al.
Pubblicazione: (2025)

Learning-based Detection of GPS Spoofing Attack for Quadrotors
di: Wang, Pengyu, et al.
Pubblicazione: (2025)

Imitative Membership Inference Attack
di: Du, Yuntao, et al.
Pubblicazione: (2025)

Model Extraction Attacks Revisited
di: Liang, Jiacheng, et al.
Pubblicazione: (2023)

Attacks on fairness in Federated Learning
di: Rance, Joseph, et al.
Pubblicazione: (2023)

Transferable Availability Poisoning Attacks
di: Liu, Yiyong, et al.
Pubblicazione: (2023)

Privacy Attacks in Decentralized Learning
di: Mrini, Abdellah El, et al.
Pubblicazione: (2024)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
di: Paracha, Anum, et al.
Pubblicazione: (2025)

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
di: Simonetto, Thibault, et al.
Pubblicazione: (2024)

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
di: Nie, Yuzhou., et al.
Pubblicazione: (2024)

Effective backdoor attack on graph neural networks in link prediction tasks
di: Dai, Jiazhu, et al.
Pubblicazione: (2024)