UniCode, a novel two-stage defense framework against identifier renaming, is proposed, one of the most effective modifications influencing DCMs’ robustness, and effectively aligns the distributions between the training data and the adversarial test samples, thereby significantly enhancing model robustness.
The first systematic study of model editing as a model-level hardening mechanism for secure code generation is conducted, evaluating 3 state-of-the-art editing methods across diverse LLM families and comparing them with CoSec, a representative inference-time approach, focusing on security, robustness, generalization, and functional correctness.
Weifeng Sun, Quanjun Zhang, Yuchen Chen 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
: 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
This paper introduces a programming language-agnostic, transferable, adversarial attack that exploits this CLM vulnerability and demonstrates that this attack, even when computed using smaller code embedding models, is highly effective and transferable to larger, closed-source embedding models.
Kaicheng Wang, Liyan Huang, Jesse Thomason et al.· 0 citations
A Unidirectional Safety Gate (USG) is proposed, instantiated as a Null Space Cubic Layer together with an Inverse Adapter inserted after the final Transformer layer, suggesting that release-time representation-space blocking can raise the cost of malicious downstream adaptation without requiring downstream cooperation.
Yuxuan Huang, Xingyu Zeng, Tianhang Zheng et al.· 0 citations
Such failures are called Representation-Confusion Attacks in Reverse Engineering (RARE): the pipeline promotes a correctly extracted observation to instruction authority, claim-validating evidence, or trusted analysis state without the authority or support that role requires.
Igor Santos-Grueiro· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
