# AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications

arXiv: https://arxiv.org/abs/2512.20164 · HTML: https://mlsanity.com/paper/2512.20164/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 77 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 30 of 40)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [MART: Improving LLM Safety with Multi-round Automatic Red-Teaming](https://mlsanity.com/paper/2311.07689/) (2023)
- [Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable](https://mlsanity.com/paper/2503.00555/) (2025)
- [A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models](https://mlsanity.com/paper/2402.13457/) (2024)
- [Look at the First Sentence: Position Bias in Question Answering](https://mlsanity.com/paper/2004.14602/) (2020)
- [STAIR: Improving Safety Alignment with Introspective Reasoning](https://mlsanity.com/paper/2502.02384/) (2025)
- [Design Patterns for Securing LLM Agents against Prompt Injections](https://mlsanity.com/paper/2506.08837/) (2025)
- [Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples](https://mlsanity.com/paper/2209.02128/) (2022)
- [Against The Achilles' Heel: A Survey on Red Teaming for Generative Models](https://mlsanity.com/paper/2404.00629/) (2024)
- [RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability](https://mlsanity.com/paper/2504.10081/) (2025)
- [From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training](https://mlsanity.com/paper/2508.09224/) (2025)
- [Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models](https://mlsanity.com/paper/2502.18695/) (2025)
- [Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey](https://mlsanity.com/paper/2309.13933/) (2023)
- [Serial Position Effects of Large Language Models](https://mlsanity.com/paper/2406.15981/) (2024)

## Built on by (most cited first, 3 of 3)

- [Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening](https://mlsanity.com/paper/2605.28999/) (2026)
- [Beyond the Resum'e: A Rubric-Aware Automatic Interview System for Information Elicitation](https://mlsanity.com/paper/2603.01775/) (2026)
- [ResumeShield: Channel Separation and an Open Benchmark for Indirect Prompt Injection in AI Resume Screening](https://mlsanity.com/paper/2609.20188/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task. Notably, while defenses may exist for mature domains such as code review, they are often absent in other common applications such as resume screening and peer review. This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types. We evaluate two defense mechanisms: prompt-based defenses achieve 10.1% attack reduction with 12.5% false rejection increase, while our proposed FIDS (Foreign Instruction Detection through Separation) using LoRA adaptation achieves 15.4% attack reduction with 10.4% false rejection increase. The combined approach provides 26.3% attack reduction, demonstrating that training-time defenses outperform inference-time mitigations in both security and utility preservation.