Dec 2025· International Journal of Machine Learning and Cybernetics· Vol 17· 3 citations· ⚡ 1 influential· 77 references
Computer Science
TL;DR
A benchmark for this vulnerability in LLM-based resume screening is introduced: 463 job-candidate pairs drawn from a 14-domain corpus, with the evaluated sample covering 13 domains, attacked through a taxonomy of four attack types and four injection positions.
Abstract
Large Language Models (LLMs) are increasingly used to automate high-stakes screening decisions, yet they can be manipulated by adversarial instructions hidden in the documents they evaluate. This paper introduces a benchmark for this vulnerability in LLM-based resume screening: 463 job-candidate pairs drawn from a 14-domain corpus, with the evaluated sample covering 13 domains, attacked through a taxonomy of four attack types and four injection positions (16 attack configurations). Across 12 model configurations covering open-weight and proprietary models, some attack types exceed 80% attack success rate (ASR) when the injected content reaches the model, and attacks upgrade up to 73.4% of candidates unanimously rejected by human annotators. The hidden-content attacks assume the resume text or HTML reaches the model; an end-to-end parser-layer analysis shows that style-aware sanitization removes most of them before classification, whereas visible-text attacks survive. We evaluate prompt-based defenses on all 12 model configurations and our proposed FIDS (Foreign Instruction Detection through Separation), a fine-tuning defense, on Qwen3-8B, the one base model we could fine-tune. On Qwen3-8B, in paired configuration-level comparisons against a common no-defense baseline, prompt-based defense reduces ASR by 10.1 percentage points (pp; 95% bootstrap CI [6.3, 14.3]), FIDS by 15.4 pp (95% CI [8.8, 23.4]), and their combination by 26.3 pp (95% CI [18.2, 35.0]), at the cost of also downgrading candidates the undefended model had accepted (a proxy for false rejections), by 12.5, 10.4, and 19.4 pp respectively. No defense eliminates the attacks, training-time and prompt-only defenses have comparable utility costs, and whether these trade-offs carry over to the proprietary models we cannot fine-tune is left to future work.
A defense taxonomy spanning three axes, namely prompt-level, inference-time, and training-time interventions, is proposed, within which 30 mitigation mechanisms published from 2024 onwards are systematically analyzed, demonstrating that no single defense mechanism provides comprehensive protection, and that robust deployment mandates layered, complementary strategies.
Berkay Özçam, Mustafa Kara, Muhammet Ali Aydin et al.· Electronics· 0 citations
: Large language models are increasingly being deployed in safety-critical domains, yet remain vulnerable to jailbreak attacks that circumvent safety alignments. This systematic review synthesizes empirical jailbreak research published between 2024 and 2025, using a PRISMA-guided search protocol, followed by BERTopic-based topic modeling. The analysis identifies eight main jailbreak categories: optimization-based, ge-netic/evolutionary, iterative refinement, semantic/persuasion-based, decomposition, context/generation-level, visual/encoding and fuzzing attacks, and characterizes their effectiveness, efficiency, and transferability across open-source and proprietary models, including Llama-2/3, Vicuna, GPT-3.5/4, Claude, Gemini, and DeepSeek-V3. Results show that simple configuration and context-level attacks can match the near-perfect attack success rates of sophisticated white-box optimization methods on models such as Llama-2, while requiring far fewer queries and no parameter access, highlighting a gap between research focus and practical threat severity. The review further identifies five recurring vulnerability mechanisms: representation-level gaps, execution-priority manipulation, semantic fragmentation, gradient-space exploitation and persuasion susceptibility, and documents family-specific vulnerability patterns, with open-source Llama-based models consistently more exposed than safety-enhanced architectures such as Claude. Diverse methods, uneven focus on models and publication bias limit how broadly results apply. Nonetheless, the review reveals that weaknesses in safety alignment persist across successive LLM generations, urging that effective defenses must address all eight attack categories rather than isolated techniques.
Meda Račaitytė, Hélder Bastos, R. Ribeiro et al.· International Conference on...· 0 citations
A four-layer taxonomy mapping 13 vulnerability types across perception, brain, action, and interaction layers is contributed, and seven open problems centered on containment are identified.
Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan Ansari· 0 citations
The increasing deployment of Large Language Models (LLMs) in critical infrastructure has introduced a class of security risks that remain insufficiently characterised and poorly tooled in practice. Attack vectors including prompt injection, jailbreaking, code execution facilitation, covert data exfiltration, and training data poisoning present quantifiable threats to systems that rely on LLM outputs, yet no lightweight, provider-agnostic tool exists to measure these risks systematically. This paper presents VectorSec, an open-source, web-based LLM security scanner built with Python and Dash. The tool executes a structured test suite of 320 adversarial prompts spanning 16 vulnerability categories aligned with the OWASP Top 10 for LLMs. Each response is scored through a four-stage pipeline combining pattern matching, sentiment analysis, semantic similarity, and secondary LLM verification. Evaluation across three open-source models demonstrates that pattern-matching-only filtering misses approximately 15% of High and Critical findings that semantic verification correctly identifies, motivating the multi-layer design. VectorSec provides interactive dashboard reporting, real-time progress tracking, and audit-ready PDF and CSV exports, lowering the barrier to structured LLM security assessment in operational settings.
M. Yamin· International Conference on...· 0 citations
Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defenses require access to model weights or internals, making them difficult to apply to black-box deployments. We propose AlcaTRAz (Anchored Tree-Rule defense Against jailbreaks), a prompt-level defense based on rule trees that operates exclusively on the input text and requires no modification or retraining of the target model. The method automatically learns a transferable transformation rule that inserts controlled character-level perturbations at selected positions, thereby disrupting structural regularities exploited by jailbreak attacks while largely preserving the model's utility on benign queries. We evaluate the proposed method across 33 open-weight models, 22 jailbreak attack types, and a benchmark of short, single-turn benign questions, comparing against three representative prompt-level baselines (Llama Guard, RA-LLM, Goal Prioritization). Among the compared defenses, AlcaTRAz achieves the best composite security and functionality score in 73.4 % of model-attack combinations and shifts the aggregate score from a modal value of 10 (maximal-severity response to the malicious request) in the undefended setting to a modal value of 2 (near-refusal) after defense, while keeping the mean benign score within 0.27 points of the undefended baseline (8.35 vs. 8.62 on a 0-10 scale). AlcaTRAz substantially reduces but does not eliminate jailbreak success: a high-severity tail remains, and we do not consider adaptive attackers, so we position it as one layer within a defense-in-depth strategy rather than a standalone guarantee.
J. Res, Petr Kaska, Martin Perešíni et al.· 0 citations
This work presents a two-phase evaluation of ten Llama variants using the OWASP Top 10 for LLM Applications, and applies nine encoding obfuscations to the same prompts, which fully bypasses all text-only models.
Nourin Shahin, Izzat Alsmadi· Practice and Experience in A...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
