Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dankworth, Raik, Schwalbe, Gesina
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Power side-channel leakage localization through adversarial training of deep neural networks
par: Gammell, Jimmy, et autres
Publié: (2024)

Can sparsity improve the privacy of neural networks?
par: Gonon, Antoine, et autres
Publié: (2023)

ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
par: Clifford, Eleanor, et autres
Publié: (2022)

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

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

Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning
par: Jiang, Yu, et autres
Publié: (2024)

Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
par: Giri, Nandakrishna, et autres
Publié: (2026)

In-network Attack Detection with Federated Deep Learning in IoT Networks: Real Implementation and Analysis
par: Chaudhary, Devashish, et autres
Publié: (2026)

SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
par: Xu, Haotian, et autres
Publié: (2025)

Towards Automatic Hands-on-Keyboard Attack Detection Using LLMs in EDR Solutions
par: Portnoy, Amit, et autres
Publié: (2024)

LFFR: Logistic Function For (single-output) Regression
par: Chiang, John
Publié: (2024)

Sybil-based Virtual Data Poisoning Attacks in Federated Learning
par: Zhu, Changxun, et autres
Publié: (2025)

FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs
par: Meerza, Syed Irfan Ali, et autres
Publié: (2026)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
par: Gao, Yue, et autres
Publié: (2023)

Sparsity in neural networks can improve their privacy
par: Gonon, Antoine, et autres
Publié: (2023)

Using Graph Theory for Improving Machine Learning-based Detection of Cyber Attacks
par: Zonneveld, Giacomo, et autres
Publié: (2024)

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning
par: Wang, Yujing, et autres
Publié: (2024)

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
par: Pham, Dzung, et autres
Publié: (2023)

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
par: Guo, Ji, et autres
Publié: (2026)

FedRecAttack: Model Poisoning Attack to Federated Recommendation
par: Rong, Dazhong, et autres
Publié: (2022)

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
par: Jin, Zhibo, et autres
Publié: (2024)

CST-AFNet: A dual attention-based deep learning framework for intrusion detection in IoT networks
par: Ishtiaq, Waqas, et autres
Publié: (2025)

Attack Smarter: Attention-Driven Fine-Grained Webpage Fingerprinting Attacks
par: Yuan, Yali, et autres
Publié: (2025)

Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
par: Obadinma, Stephen, et autres
Publié: (2024)

Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks
par: Zhang, Jiahao, et autres
Publié: (2026)

Attack and Defense of Deep Learning Models in the Field of Web Attack Detection
par: Shi, Lijia, et autres
Publié: (2024)

CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
par: Mu, Fangwen, et autres
Publié: (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
par: Peinemann, Thorsten, et autres
Publié: (2025)

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
par: Yao, Yuan, et autres
Publié: (2025)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
par: Zhan, Qiusi, et autres
Publié: (2025)

Learning-based Detection of GPS Spoofing Attack for Quadrotors
par: Wang, Pengyu, et autres
Publié: (2025)

Imitative Membership Inference Attack
par: Du, Yuntao, et autres
Publié: (2025)

Model Extraction Attacks Revisited
par: Liang, Jiacheng, et autres
Publié: (2023)

Attacks on fairness in Federated Learning
par: Rance, Joseph, et autres
Publié: (2023)

Transferable Availability Poisoning Attacks
par: Liu, Yiyong, et autres
Publié: (2023)

Privacy Attacks in Decentralized Learning
par: Mrini, Abdellah El, et autres
Publié: (2024)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
par: Paracha, Anum, et autres
Publié: (2025)

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
par: Simonetto, Thibault, et autres
Publié: (2024)

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
par: Nie, Yuzhou., et autres
Publié: (2024)

Effective backdoor attack on graph neural networks in link prediction tasks
par: Dai, Jiazhu, et autres
Publié: (2024)