FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2885673189> ?p ?o ?g. }

• W2885673189 abstract "To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided based on when they occur: if an attack occurs during training, it is known as a poisoning attack, and if it occurs during inference (after training) it is termed an evasion attack. Poisoning attacks compromise the training process by corrupting the data with malicious examples, while evasion attacks use adversarial examples to disrupt entire classification process. Defenses proposed against such attacks include techniques to recognize and remove malicious data, train a model to be insensitive to such data, and mask the model's structure and parameters to render attacks more challenging to implement. Furthermore, the privacy of the data involved in model training is also threatened by attacks such as the model-inversion attack, or by dishonest service providers of AI applications. To maintain data privacy, several solutions that combine existing data-privacy techniques have been proposed, including differential privacy and modern cryptography techniques. In this paper, we describe the notions of some of methods, e.g., homomorphic encryption, and review their advantages and challenges when implemented in deep-learning models." @default.
• W2885673189 created "2018-08-22" @default.
• W2885673189 creator A5000924405 @default.
• W2885673189 creator A5008547463 @default.
• W2885673189 creator A5010990289 @default.
• W2885673189 creator A5017279448 @default.
• W2885673189 creator A5018672599 @default.
• W2885673189 creator A5056602268 @default.
• W2885673189 creator A5086877012 @default.
• W2885673189 date "2018-07-31" @default.
• W2885673189 modified "2023-09-26" @default.
• W2885673189 title "Security and Privacy Issues in Deep Learning" @default.
• W2885673189 cites W104209573 @default.
• W2885673189 cites W1557833142 @default.
• W2885673189 cites W1617650991 @default.
• W2885673189 cites W1787224781 @default.
• W2885673189 cites W1821462560 @default.
• W2885673189 cites W1901129140 @default.
• W2885673189 cites W1973124816 @default.
• W2885673189 cites W1985123706 @default.
• W2885673189 cites W1992282993 @default.
• W2885673189 cites W2010523825 @default.
• W2885673189 cites W2027595342 @default.
• W2885673189 cites W2031533839 @default.
• W2885673189 cites W2043944888 @default.
• W2885673189 cites W2051267297 @default.
• W2885673189 cites W2053637704 @default.
• W2885673189 cites W2055663168 @default.
• W2885673189 cites W2064675550 @default.
• W2885673189 cites W2072128103 @default.
• W2885673189 cites W2083842231 @default.
• W2885673189 cites W2083847133 @default.
• W2885673189 cites W2088492763 @default.
• W2885673189 cites W2103154003 @default.
• W2885673189 cites W2103559027 @default.
• W2885673189 cites W2108598243 @default.
• W2885673189 cites W2108834246 @default.
• W2885673189 cites W2109426455 @default.
• W2885673189 cites W2112380340 @default.
• W2885673189 cites W2130325614 @default.
• W2885673189 cites W2132172731 @default.
• W2885673189 cites W2138865266 @default.
• W2885673189 cites W2142544755 @default.
• W2885673189 cites W2156030242 @default.
• W2885673189 cites W2157331557 @default.
• W2885673189 cites W2166160300 @default.
• W2885673189 cites W2167372639 @default.
• W2885673189 cites W2168231600 @default.
• W2885673189 cites W2177209050 @default.
• W2885673189 cites W2180612164 @default.
• W2885673189 cites W2194775991 @default.
• W2885673189 cites W2233194383 @default.
• W2885673189 cites W2267126114 @default.
• W2885673189 cites W2293844262 @default.
• W2885673189 cites W2319920447 @default.
• W2885673189 cites W2342408547 @default.
• W2885673189 cites W2402144811 @default.
• W2885673189 cites W2405601665 @default.
• W2885673189 cites W2408141691 @default.
• W2885673189 cites W2432142698 @default.
• W2885673189 cites W2435473771 @default.
• W2885673189 cites W2460937040 @default.
• W2885673189 cites W2464708700 @default.
• W2885673189 cites W2473418344 @default.
• W2885673189 cites W2513180554 @default.
• W2885673189 cites W2520442116 @default.
• W2885673189 cites W2530417694 @default.
• W2885673189 cites W2532781556 @default.
• W2885673189 cites W2535690855 @default.
• W2885673189 cites W2535873859 @default.
• W2885673189 cites W2538525524 @default.
• W2885673189 cites W2541884796 @default.
• W2885673189 cites W2543927648 @default.
• W2885673189 cites W2548275288 @default.
• W2885673189 cites W2554750353 @default.
• W2885673189 cites W2557044351 @default.
• W2885673189 cites W2557283755 @default.
• W2885673189 cites W2561498661 @default.
• W2885673189 cites W2572659264 @default.
• W2885673189 cites W2585580772 @default.
• W2885673189 cites W2590523583 @default.
• W2885673189 cites W2591602089 @default.
• W2885673189 cites W2591882872 @default.
• W2885673189 cites W2593892853 @default.
• W2885673189 cites W2594867206 @default.
• W2885673189 cites W2594877703 @default.
• W2885673189 cites W2597603852 @default.
• W2885673189 cites W2600838321 @default.
• W2885673189 cites W2603433898 @default.
• W2885673189 cites W2603766943 @default.
• W2885673189 cites W2604147826 @default.
• W2885673189 cites W2605409611 @default.
• W2885673189 cites W2613718673 @default.
• W2885673189 cites W2618043096 @default.
• W2885673189 cites W2620512600 @default.
• W2885673189 cites W2625220439 @default.
• W2885673189 cites W2701059868 @default.
• W2885673189 cites W2729742878 @default.
• W2885673189 cites W2732746601 @default.
• W2885673189 cites W2736899637 @default.

• next