arXiv AI
JANUS: Synthesizing Cross-Layer Defenses Against Web Deserialization Attacks
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 12
Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal
The paper examines how fine‑tuned defenses against prompt injection in large language models can be audited before deployment. By leveraging intermediate checkpoints from the fine‑tuning process, the authors create strong optimization‑based attacks (e.g., GCG and BEAST) that dramatically increase attack success rates—from near zero to up to 96%—against state‑of‑the‑art defenses. This demonstrates that current empirical evaluations often overestimate robustness and that pre‑deployment stress‑testing can uncover real vulnerabilities.
arXiv Computation and Language
Oct 28
DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization
The paper introduces DYNASHIELD, a black-box moving target defense for large language models that dynamically customizes decoding hyperparameters and system prompts during inference. It first identifies decoding configurations that lower the probability of successful jailbreak attacks, then samples from a weighted pool of these configurations to add controlled variability to the model’s behavior. Experiments on seven open-source LLMs and four state-of-the-art jailbreak attacks show that DYNASHIELD significantly reduces attack success rates while preserving response quality and adding minimal inference overhead.
arXiv AI
Jul 1
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
arXiv AI
Oct 15
ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?
ProtoArena is a new black-box benchmark that tests AI agents on 80 cross‑component vulnerability‑exploitation environments across 11 protocol and application domains and 7 attack categories. It evaluates agents at three information levels—guided reproduction, exploitation with context, and effect‑directed black‑box exploration—using a hybrid verifier that combines rule‑based checks with LLM review of traffic and logs. In experiments, Claude Opus 4.8 achieved the highest success rates, reaching 48.8% under guided conditions and 12.5% in effect‑directed black‑box scenarios, while also demonstrating significant DNSBomb optimization performance.
arXiv AI
Oct 27
The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
The paper examines how AI agents that interact directly with web service backends alter the exploitation of existing web vulnerabilities. Using the VELA benchmark, which includes 44 vulnerabilities across twelve application families, the authors evaluate three commercial agents and find that exploitability is largely determined by the interface design rather than the agent itself, with 91% of vulnerabilities remaining exploitable under the reference configuration. Interface restrictions can reduce attack success, yet the agents generally do not introduce new failures, and in some cases even complete attacks that users omitted.
arXiv AI
Oct 16
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
INFUSE is a new benchmark that tests indirect prompt injection (IPI) in large‑language‑model agents performing long‑horizon workflows. It contains 40 realistic tasks and 56 attack scenarios across five threat categories, with attacks injected through realistic interaction surfaces rather than just initial prompts. The study evaluated 19 LLMs, generating over 41,000 adversarial trajectories and found mean attack success rates of 19.6% (LLM evaluation) and 15.4% (heuristic verification), while prompt‑level hardening reduced success from 58.2% to 14.3%.