Research map / Learning theory and algorithms / Submodular and game algorithms
Deception through Half-Truths
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Combine the approximation algorithm with the hill-climbing heuristic by choosing the better mask | Additive DBNM masking · Random general and additive networks | utility | Helped |
| Combine the approximation algorithm with the hill-climbing heuristic by choosing the better mask | Additive DBNM masking · Networks constructed adversarially against the heuristic | utility | Helped |
| Use hill-climbing alone, greedily adding the variable with the largest immediate increase in utility | Additive DBNM masking · Constructed heuristic counterexample | utility ratio to optimal: ε | Hurt |
| Restrict transitions to depend linearly on parent values | DBNM and TDBNM · Linear Bayesian networks | computational complexity | Helped |
| Restrict transitions to depend additively on the sum of parent values | DBNM and TDBNM · Monotone additive networks | approximation guarantee: n-approximation | Mixed |
Closest papers by meaning
- Deception in Finitely Repeated Security Games (AAAI 2019 · similarity 0.85)
- Practical Bayes-Optimal Membership Inference Attacks (NeurIPS 2025 · similarity 0.82)
- Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs (NeurIPS 2025 · similarity 0.82)
- Sequential Membership Inference Attacks (NeurIPS 2026 · similarity 0.82)
- Detecting Strategic Deception with Linear Probes (ICML 2025 · similarity 0.81)
- Disparate Impact on Group Accuracy of Linearization for Private Inference (ICML 2024 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.