Intra Frame Interpolation with H.264 intra prediction method

Wang, Jong-Tzy; Su, Huai-Sheng

doi:10.1109/icmlc.2010.5580741

Cited by 5 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the wide adoption of bandit algorithms in practice, increasing amount of research attention has been spent on adversarial attacks against such algorithms to understand their robustness implications. To date, most effort has been focused on data poisoning attacks against stochastic MAB (Jun et al 2018;Liu and Shroff 2019) and linear contextual bandit (Garcelon et al 2020;Wang, Xu, and Wang 2022) algorithms. And these methods follow the same principle: deliberately lower the reward of non-target arms, to deceive the learner to pull the target arm a linear number of times.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

Wang,

Wang

2024

AAAI

View full text Add to dashboard Cite

Adversarial attacks against stochastic multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and find most existing attacks can be easily detected by our proposed detection method based on the test of homogeneity, due to their aggressive nature in reward manipulations. This motivates us to study the notion of stealthy attack against stochastic MABs and investigate the resulting attackability. Our analysis shows that against two popularly employed MAB algorithms, UCB1 and $\epsilon$-greedy, the success of a stealthy attack depends on the environmental conditions and the realized reward of the arm pulled in the first round. We also analyze the situation for general MAB algorithms equipped with our attack detection method and find that it is possible to have a stealthy attack that almost always succeeds. This brings new insights into the security risks of MAB algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

“…As a result, most existing MAB algorithms can be easily protected by such a detection method, with little impact on their regret. This provides a new perspective to examine the robustness or the so-called attackability (Wang, Xu, and Wang 2022) of MAB algorithms under the presence of attack detection methods.…”

Section: Introductionmentioning

confidence: 99%

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

Wang,

Wang

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Based on our predictive model and interpretability analysis, we propose a quantitative strategy to enhance companies' digital transformation [48]. Among the eight key features, namely RDeapoinr, Lev, and ATO, adjusting the latter three is relatively easier compared to the remaining features, which are relatively fixed.…”

Section: Improve Quantitative Adjustment Strategies For Digital Trans...mentioning

confidence: 99%

Prediction of digital transformation of manufacturing industry based on interpretable machine learning

Zhu,

Liu,

Chen

2024

PLoS ONE

View full text Add to dashboard Cite

The enhancement of digital transformation is of paramount importance for business development. This study employs machine learning to establish a predictive model for digital transformation, investigates crucial factors that influence digital transformation, and proposes corresponding improvement strategies. Initially, four commonly used machine learning algorithms are compared, revealing that the Extreme tree classification (ETC) algorithm exhibits the most accurate prediction. Subsequently, through correlation analysis and recursive elimination, key features that impact digital transformation are selected resulting in the corresponding feature subset. Shapley Additive Explanation (SHAP) values are then employed to perform an interpretable analysis on the predictive model, elucidating the effects of each key feature on digital transformation and obtaining critical feature values. Lastly, informed by practical considerations, we propose a quantitative adjustment strategy to enhance the degree of digital transformation in enterprises, which provides guidance for digital development.

show abstract

“…To understand teaching, a special case is first considered where the optimal arm k † is known by the server. Then, the goal is to assign adjustments to have the clients pull the pre-specified arm k † as much as possible, which is mathematically the same as the data-poisoning MAB problem [22], [24], [25], [49], where adjustments are phrased as "attacks". In such scenarios, the server can achieve R m (T ) = O(log(T )) and C m (T ) = O(log(T )) for each m ∈ [M ] by adjusting rewards from all arms except arm k † to 0's [26].…”

Section: Two Coupled Tasks and Design Objectivesmentioning

confidence: 99%

An Attackability Perspective on No-Sensing Adversarial Multi-player Multi-armed Bandits

Shi

Shen

2021

2021 IEEE International Symposium on Information Theory (ISIT)

View full text Add to dashboard Cite

Most of the existing federated multi-armed bandits (FMAB) designs are based on the presumption that clients will implement the specified design to collaborate with the server. In reality, however, it may not be possible to modify the client's existing protocols. To address this challenge, this work focuses on clients who always maximize their individual cumulative rewards, and introduces a novel idea of "reward teaching", where the server guides the clients towards global optimality through implicit local reward adjustments. Under this framework, the server faces two tightly coupled tasks of bandit learning and target teaching, whose combination is non-trivial and challenging. A phased approach, called Teaching-After-Learning (TAL), is first designed to encourage and discourage clients' explorations separately. General performance analyses of TAL are established when the clients' strategies satisfy certain mild requirements. With novel technical approaches developed to analyze the warmstart behaviors of bandit algorithms, particularized guarantees of TAL with clients running UCB or ε-greedy strategies are then obtained. These results demonstrate that TAL achieves logarithmic regrets while only incurring logarithmic adjustment costs, which is order-optimal w.r.t. a natural lower bound. As a further extension, the Teaching-While-Learning (TWL) algorithm is developed with the idea of successive arm elimination to break the non-adaptive phase separation in TAL. Rigorous analyses demonstrate that when facing clients with UCB1, TWL outperforms TAL in terms of the dependencies on sub-optimality gaps thanks to its adaptive design. Experimental results demonstrate the effectiveness and generality of the proposed algorithms.

show abstract

Intra Frame Interpolation with H.264 intra prediction method

Cited by 5 publications

References 7 publications

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

Prediction of digital transformation of manufacturing industry based on interpretable machine learning

An Attackability Perspective on No-Sensing Adversarial Multi-player Multi-armed Bandits

Contact Info

Product

Resources

About