Constrained Diffusion for Code (CDC) integrates constraint satisfaction into the reverse denoising process of discrete diffusion models via constraint-aware operators that use optimization and program analysis to steer generation toward feasible programs.
Asleep at the keyboard? assessing the security of github copilot’s code contributions
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
NES systems in AI IDEs expand attack surfaces via context poisoning from imperceptible actions and global codebase retrieval, with professional developers largely unaware of the risks.
Analysis of 9,799 human-reviewed agentic PRs shows only 35.7% of rejections reflect clear agent failures, with 31.2% due to workflow constraints and 33.1% lacking clear rationale, plus notable interaction differences across agents.
Co-locating tests with implementation code yields substantially higher preservation and correctness in foundation-model-generated programs than separated test syntax.
Adversarial competition between attacker and defender teams generates diverse multi-turn conversational data that improves LLM performance on secure code generation benchmarks by 18-29%.
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
PaLM 540B demonstrates continued scaling benefits by setting new few-shot SOTA results on hundreds of benchmarks and outperforming humans on BIG-bench.
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
citing papers explorer
-
Constrained Code Generation with Discrete Diffusion
Constrained Diffusion for Code (CDC) integrates constraint satisfaction into the reverse denoising process of discrete diffusion models via constraint-aware operators that use optimization and program analysis to steer generation toward feasible programs.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
"Tab, Tab, Bug": Security Pitfalls of Next Edit Suggestions in AI-Integrated IDEs
NES systems in AI IDEs expand attack surfaces via context poisoning from imperceptible actions and global codebase retrieval, with professional developers largely unaware of the risks.
-
Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
Analysis of 9,799 human-reviewed agentic PRs shows only 35.7% of rejections reflect clear agent failures, with 31.2% due to workflow constraints and 33.1% lacking clear rationale, plus notable interaction differences across agents.
-
Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation
Co-locating tests with implementation code yields substantially higher preservation and correctness in foundation-model-generated programs than separated test syntax.
-
Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition
Adversarial competition between attacker and defender teams generates diverse multi-turn conversational data that improves LLM performance on secure code generation benchmarks by 18-29%.
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
PaLM: Scaling Language Modeling with Pathways
PaLM 540B demonstrates continued scaling benefits by setting new few-shot SOTA results on hundreds of benchmarks and outperforming humans on BIG-bench.
-
StarCoder: may the source be with you!
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.