English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although local differential privacy (LDP) protects individual users' datafrom inference by an untrusted data curator, recent studies show that anattacker can launch a data poisoning attack from the user side to injectcarefully-crafted bogus data into the LDP protocols in order to maximally skewthe final estimate by the data curator.  In this work, we further advance this knowledge by proposing a newfine-grained attack, which allows the attacker to fine-tune and simultaneouslymanipulate mean and variance estimations that are popular analytical tasks formany real-world applications. To accomplish this goal, the attack leverages thecharacteristics of LDP to inject fake data into the output domain of the localLDP instance. We call our attack the output poisoning attack (OPA). We observea security-privacy consistency where a small privacy loss enhances the securityof LDP, which contradicts the known security-privacy trade-off from prior work.We further study the consistency and reveal a more holistic view of the threatlandscape of data poisoning attacks on LDP. We comprehensively evaluate ourattack against a baseline attack that intuitively provides false input to LDP.The experimental results show that OPA outperforms the baseline on threereal-world datasets. We also propose a novel defense method that can recoverthe result accuracy from polluted data collection and offer insight into thesecure LDP design.

Fine-grained Poisoning Attack to Local Differential Privacy Protocols for Mean and Variance Estimation