 |
 |
 |
 |
 |
 |
||
 |
 |
 |
 |
 |
| 5 | 1/1 | 返回列表 |
| 查看: 784 | 回復(fù): 7 | |||
| 【有獎(jiǎng)交流】積極回復(fù)本帖子，參與交流，就有機(jī)會分得作者 liyangnpu 的 13 個(gè)金幣 ，回帖就立即獲得 1 個(gè)金幣，每人有 1 次機(jī)會 | |||
| 當(dāng)前只顯示滿足指定條件的回帖，點(diǎn)擊這里查看本話題的所有回帖 | |||
[交流]
【征稿】Future-Generation Attack and Defense in Neural Networks (FGADNN)
|
|||
|
Special Issue -- Future-Generation Attack and Defense in Neural Networks (FGADNN) Aims & Scopes Neural Networks have demonstrated great success in many fields, e.g., natural language processing, image analysis, speech recognition, recommender system, physiological computing, etc. However, recent studies revealed that neural networks are vulnerable to adversarial attacks. The vulnerability of neural networks, which may hinder their adoption in high-stake scenarios. Thus, understanding their vulnerability and developing robust neural networks have attracted increasing attention. To understand and accommodate the vulnerability of neural networks, various attack and defense techniques have been proposed. According to the stage that the adversarial attack is performed, there are two types of attacks: poisoning attacks and evasion attacks. The former happens at the training stage, to create backdoors in the machine learning model by adding contaminated examples to the training set. The latter happens at the test stage, by adding deliberately designed tiny perturbations to benign test samples to mislead the neural network. According to how much the attacker knows about the target model, there are white-box, gray-box, and black-box attacks. According to the outcome, there are targeted attacks and non-targeted (indiscriminate) attacks. There are also many different attack scenarios, resulted from different combinations of these attack types. Several different adversarial defense strategies have also been proposed, e.g., data modification, which modifies the training set in the training stage or the input data in the test stage, through adversarial training, gradient hiding, transferability blocking, data compression, data randomization, etc.; model modification, which modifies the target model directly to increase its robustness, by regularization, defensive distillation, feature squeezing, using a deep contractive network or a mask layer, etc.; and, auxiliary tools, which may be additional auxiliary machine learning models to robustify the primary model, e.g., adversarial detection models, or defense generative adversarial nets (defense-GAN), high-level representation guided denoiser, etc. Because of the popularity, complexity, and lack of interpretability of neural networks, it is expected that more attacks will immerge, in various different scenarios and applications. It is critically important to develop strategies to defend against them. This special issue focuses on adversarial attacks and defenses in various future-generation neural networks, e.g., CNNs, LSTMs, ResNet, Transformers, BERT, spiking neural networks, and graph neural networks. We invite both reviews and original contributions, on the theory (design, understanding, visualization, and interpretation) and applications of adversarial attacks and defenses, in future-generation natural language processing, computer vision systems, speech recognition, recommender system, etc. Topics of interest include, but are not limited to: • Novel adversarial attack approaches • Novel adversarial defense approaches • Model vulnerability discovery and explanation • Trust and interpretability of neural network • Attacks and/or defenses in NLP • Attacks and/or defenses in recommender systems • Attacks and/or defenses in computer vision • Attacks and/or defenses in speech recognition • Attacks and/or defenses in physiological computing • Adversarial attack and defense various future-generation applications Evaluation Criterion • Novelty of the approach (how is it different from existing ones?) • Technical soundness (e.g., rigorous model evaluation) • Impact (how does it change the state-of-the-arts) • Readability (is it clear what has been done) • Reproducibility and open source: pre-registration if confirmatory claims are being made (e.g., via osf.io), open data, materials, code as much as ethically possible. Submission Instructions All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Authors should prepare their manuscript according to the Guide for Authors available from the online submission page of the Future Generation Computer Systems at https://ees.elsevier.com/fgcs/. Authors should select “VSI: NNVul” when they reach the “Article Type” step in the submission process. Inquiries, including questions about appropriate topics, may be sent electronically to liyangnpu@nwpu.edu.cn. Please make sure to read the Guide for Authors before writing your manuscript. The Guide for Authors and link to submit your manuscript is available on the Journal’s homepage at: https://www.journals.elsevier.co ... n-computer-systems. Important Dates ● Manuscript Submission Deadline: 20th June 2022 ● Peer Review Due: 30th July 2022 ● Revision Due: 15th September 2022 ● Final Decision: 20th October 2022 |
回復(fù)此樓» 猜你喜歡
085600材料調(diào)劑 總分330
已經(jīng)有6人回復(fù)
-
歡迎211本科同學(xué)，過A區(qū)國家線，A區(qū)非偏遠(yuǎn)一本，交叉學(xué)科課題組
已經(jīng)有30人回復(fù)
-
高分子化學(xué)與物理調(diào)劑
已經(jīng)有17人回復(fù)
-
化學(xué)專業(yè)調(diào)劑
已經(jīng)有6人回復(fù)
-
0703 東華大學(xué) 理學(xué)化學(xué)均過 a 線，總分 281 求調(diào)劑
已經(jīng)有11人回復(fù)
-
材料工程調(diào)劑
已經(jīng)有6人回復(fù)
-
材料學(xué)碩318求調(diào)劑
已經(jīng)有13人回復(fù)
-
08工科求調(diào)劑
已經(jīng)有4人回復(fù)
-
A區(qū)一本交叉課題組，低分調(diào)劑，招收機(jī)械電子信息通信等交叉方向
已經(jīng)有40人回復(fù)
-
070300調(diào)劑一志愿南京大學(xué)化學(xué)專業(yè)，初試273分，有論文有專利有競賽，求調(diào)劑B區(qū)211
已經(jīng)有11人回復(fù)
» 搶金幣啦！回帖就可以得到:
-
中科院蘭化所（蘇州基地）招聘助理研究員
+5/950
-
中科院強(qiáng)磁場中心高薪誠聘博士后（有機(jī)化學(xué)）
+3/95
-
東北農(nóng)業(yè)大學(xué)—水利學(xué)院，招收農(nóng)業(yè)水土工程、土木水利碩士研究生
+1/84
-
2026藥物化學(xué)博士招生
+1/76
-
天津大學(xué) 合成生物與生物制造學(xué)院 招碩士研究生、博士研究生及博士后
+1/36
-
廣東石油化工學(xué)院劉詩詠教授團(tuán)隊(duì)化學(xué)化工、材料科學(xué)等方向尚有調(diào)劑名額
+1/34
-
江蘇高校--材料焊接、增材制造課題組招收碩士研究生
+1/17
-
26屆計(jì)算機(jī)、電子信息類、電科、控制、通信考研T j信息pp駿：74+08+76+6+20
+1/11
-
武漢科技大學(xué)周志輝教授團(tuán)隊(duì)招聘師資博后（從事高分子或特種膜分離材料與應(yīng)用）
+1/6
-
清華大學(xué)環(huán)境學(xué)院李淼教授課題組(長江學(xué)者團(tuán)隊(duì))招聘博士后
+1/6
-
青島大學(xué)物理科學(xué)學(xué)院國家級人才團(tuán)隊(duì)招收材料、化學(xué)、物理等方向博士研究生
+1/6
-
2026年西南科技大學(xué)材料與化學(xué)-功能涂層調(diào)劑招生
+1/5
-
副總監(jiān)/總監(jiān) – 北亞區(qū)
+1/5
-
0858電氣專碩364求調(diào)劑
+1/5
-
Top-88悉尼科技大學(xué)數(shù)據(jù)科學(xué)/AI 招收2027年入學(xué) 校獎(jiǎng) 博士生1到2名(國際和本地學(xué)生）
+1/5
-
中國科學(xué)院國家級人才團(tuán)隊(duì)博士后招聘啟示
+1/4
-
【博士招生】湖南大學(xué)招收電化學(xué)方向?qū)徍酥撇┦垦芯可?/a>
+1/3
-
西安工程大學(xué)環(huán)境與化學(xué)工程學(xué)院26年碩士研究生招生咨詢（26年9月入學(xué)）
+1/3
-
北京理工大學(xué)（珠海校區(qū)）何治宇教授團(tuán)隊(duì)招收26級博士生1 名 （第二批）
+1/1
-
26年材料/化學(xué)相關(guān)專業(yè)博士研究生招生 溫州大學(xué)化學(xué)與材料工程學(xué)院(26年秋季入學(xué))
+1/1
7樓2022-04-20 21:53:39
簡單回復(fù)
tzynew2樓
2022-04-20 20:45
回復(fù)
liyangnpu(金幣+1): 謝謝參與
i 發(fā)自小木蟲Android客戶端
2022-04-20 21:48
回復(fù)
liyangnpu(金幣+1): 謝謝參與
， 發(fā)自小木蟲Android客戶端
JeromeXu4樓
2022-04-20 21:04
回復(fù)
MTXSCI18樓
2022-04-20 22:44
回復(fù)
liyangnpu(金幣+1): 謝謝參與
， 發(fā)自小木蟲Android客戶端
雨月清音5樓
2022-04-20 21:47
回復(fù)
liyangnpu(金幣+1): 謝謝參與
， 發(fā)自小木蟲Android客戶端
| 最具人氣熱帖推薦 [查看全部] | 作者 | 回/看 | 最后發(fā)表 | |
|---|---|---|---|---|
|
[考研] 新疆大學(xué)地質(zhì)與礦業(yè)工程學(xué)院招生 +7 | another12 2026-03-04 | 12/600 |
|
|---|---|---|---|---|
|
|
[考研] 085701環(huán)境工程295求調(diào)劑，一志愿A區(qū)211 +3 | 等春來， 2026-03-06 | 3/150 |
|
|
[考研] 求調(diào)劑 +5 | danyyyy 2026-03-04 | 5/250 |
|
|
|
[考研] 求調(diào)劑 +3 | 泡了個(gè)椒 2026-03-04 | 4/200 |
|
|
|
[考研] 一志愿清華深研院材料專碩294分，專業(yè)課111分，本科中南大學(xué)材料，有六級，有工作經(jīng)驗(yàn) +3 | H14528 2026-03-04 | 3/150 |
|
|
|
[考研] 267調(diào)劑求助 +5 | 聰少OZ 2026-03-04 | 5/250 |
|
|
|
[考研] 304分材料專碩求調(diào)劑 +11 | qiuzhigril 2026-03-03 | 14/700 |
|
|
|
[考研] 0703化學(xué) 一志愿東北大學(xué) 279分求調(diào)劑 +4 | 聶樂平 2026-03-03 | 4/200 |
|
|
|
[考研] 武理材料工程302調(diào)劑 +3 | Doleres 2026-03-03 | 6/300 |
|
|
|
[考研] 材料化工調(diào)劑 +15 | 今夏不夏 2026-03-01 | 18/900 |
|
|
|
[考研] 281求調(diào)劑 +3 | Y?l?h 2026-03-04 | 3/150 |
|
|
|
[考研] 331求調(diào)劑 +3 | zzZ&zZ 2026-03-03 | 3/150 |
|
|
|
[考研] 289求調(diào)劑 +8 | yang婷 2026-03-02 | 10/500 |
|
|
|
[考研] 化工335求調(diào)劑 +5 | 摸摸貓貓頭 2026-03-02 | 5/250 |
|
|
|
[考研] 338求調(diào)劑 +5 | 18162027187 2026-03-02 | 6/300 |
|
|
|
[考研] 290分材料工程085601求調(diào)劑 數(shù)二英一 +8 | llx0610 2026-03-02 | 9/450 |
|
|
|
[考研] 0856求調(diào)劑285 +11 | 呂仔龍 2026-02-28 | 11/550 |
|
|
|
[考研] 材料工程274求調(diào)劑 +5 | Lilithan 2026-03-01 | 5/250 |
|
|
|
[考研] 275求調(diào)劑 +7 | 明遠(yuǎn)求學(xué) 2026-03-01 | 7/350 |
|
|
|
[考研] 材料085601調(diào)劑 +5 | 多多子. 2026-03-02 | 5/250 |
|