Researcher Evidence Record
Chia-Mu Yu
This bounded record lists 50 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.CR, cs.LG, cs.CV work dated 2009 to 2026. The record describes sources and coverage; it makes no judgment about the person.
Compiled coverage vector
A sourced case file for attributed work. It is neither a profile score nor a verdict about this researcher.
Attributed works
A bounded ledger from the Pith paper and imported-work queries. Counts and source confidence stay with each work.
-
2026 Pith paper
On the Security Implications of PQC in TLS: Handshake Exhaustion and IDS Degradation
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
RAS: Measuring LLM Safety Through Refusal Alignment
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
Quantization as a Malicious Task: Removing Quantization-Conditioned Backdoors via Task Arithmetic
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
CodeSentinel: A Three-Layer Defense Against Indirect Prompt Injection in Code Contexts
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
-
- 1 pith inbound references from cited_work_pith_inbound_counts
-
2026 Pith paper
WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2026 Pith paper
Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- backfill
- Printed name
- Chia-Mu Yu
- Author position
- 6
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: a current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
Model Reprogramming Demystified: A Neural Tangent Kernel Perspective
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 6
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
Fine-grained Manipulation Attacks to Local Differential Privacy Protocols for Data Streams
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 6
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
Data Poisoning Attacks to Locally Differentially Private Range Query Protocols
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 1 pith inbound references from cited_work_pith_inbound_counts
-
2025 Pith paper
Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
Safety Alignment Depth in Large Language Models: A Markov Chain Perspective
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2025 Pith paper
BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 6
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 1 pith inbound references from cited_work_pith_inbound_counts
-
2024 Pith paper
Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2024 Pith paper
The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2024 Pith paper
Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2024 Pith paper
Differentially Private Fine-Tuning of Diffusion Models
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 1 pith inbound references from cited_work_pith_inbound_counts
-
2024 Pith paper
Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 2 pith inbound references from cited_work_pith_inbound_counts
-
2024 Pith paper
DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2023 Pith paper
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2023 Pith paper
Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?
paper citation record paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 8
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
-
- 14 pith inbound references from cited_work_pith_inbound_counts
-
2023 Pith paper
Exploring the Benefits of Differentially Private Pre-training and Parameter-Efficient Fine-tuning for Table Transformers
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2023 Pith paper
DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2023 Pith paper
Exploring the Benefits of Visual Prompting in Differential Privacy
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2022 Pith paper
Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Meta Adversarial Perturbations
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
CAFE: Catastrophic Data Leakage in Vertical Federated Learning
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Real-World Adversarial Examples involving Makeup Application
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 5
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2021 Pith paper
Non-Singular Adversarial Robustness of Neural Networks
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2020 Pith paper
DPCrowd: Privacy-preserving and Communication-efficient Decentralized Statistical Estimation for Real-time Crowd-sourced Data
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2020 Pith paper
Privacy in Data Service Composition
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2019 Pith paper
Detecting Deepfake-Forged Contents with Separable Convolutional Neural Network and Image Segmentation
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2019 Pith paper
Locally Differentially Private Minimum Finding
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2018 Pith paper
On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2018 Pith paper
On the Limitation of MagNet Defense against $L_1$-based Adversarial Examples
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 4
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2018 Pith paper
On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 3
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2017 Pith paper
Data-Driven and Deep Learning Methodology for Deceptive Advertising and Phone Scams Detection
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2016 Pith paper
LoPub: High-Dimensional Crowdsourced Data Publication with Local Differential Privacy
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2012 Pith paper
Reducing Reconciliation Communication Cost with Compressed Sensing
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 2
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2009 Pith paper
Constrained Function Based En-Route Filtering for Sensor Networks
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
-
2009 Pith paper
Secure Multidimensional Queries in Tiered Sensor Networks
paper paper evidence challenge this paper
Sources and evidence
- Authorship source
- arxiv_oai
- Printed name
- Chia-Mu Yu
- Author position
- 1
- Identity state
- provisional
- Source confidence
- 0.7
- Review coverage
- Measured: no current Pith review exists.
- Citation counts
- No source count is attached to this work row.
Evidence apparatus
The machinery behind this record. Every lane states whether Pith measured it, did not query it, could not reach it, or withheld it.
| Lane | State | Observed | Boundary and source |
|---|---|---|---|
| identity | Measured | 2 | Canonical identity row plus public typed identifiers. source=authors, author_identifiers |
| papers | Measured | 50 of 50 bounded rows | Rows attributed to this author UUID in the Pith corpus. source=paper_authors |
| works | Measured zero | 0 of 0 bounded rows | Imported works not duplicated by the paper ledger. source=author_works |
| reviews | Measured | 10 of 50 bounded rows | Coverage count only. No review outcome is projected onto the person. source=current_verdicts |
| citations | Measured | 6 of 50 bounded rows | Counts remain itemized by work and source. source=cited_works |
| coauthors | Measured | 50 of 50 bounded rows | Shared-work edges from admitted paper rows. source=paper_authors |
| account | Unavailable | No public count of 1 bounded rows | Account metadata is separate from corpus evidence. source=users.author_id |
Public identity sources
-
name variant
Chia-Mu Yu
Enumerated research scope
- cs.CR15 rows
- cs.LG14 rows
- cs.CV11 rows
- cs.CL2 rows
- cs.NI2 rows
- cs.AI1 rows
- cs.DB1 rows
- cs.DC1 rows
- cs.IT1 rows
- math.ST1 rows
- quant-ph1 rows
- 20092 rows
- 20121 rows
- 20161 rows
- 20171 rows
- 20183 rows
- 20192 rows
- 20202 rows
- 20217 rows
- 20221 rows
- 20235 rows
- 20246 rows
- 20259 rows
- 202610 rows
Record scope
The work queries are bounded. Missing rows may mean measured zero, an unavailable source, a query that did not run, or private data that Pith withheld. The lane table keeps those cases separate.
Paper findings remain attached to papers. They do not become findings about this researcher.
Self-published account annex
Linked Pith account
Unavailable No public Pith account is linked to this corpus identity.
The account lane is self-published. Linking proves account control only and changes no corpus fact.