=======================================================================
CALL FOR PAPERS

WISTP 2027
15th International Conference on Information Security
Theory and Practice

Djerba, Tunisia | 19-21 March 2027 | Hybrid, single track

https://wistp2027.roc.cnam.fr

Proceedings published by Springer in the Lecture Notes in
Computer Science (LNCS) series
=======================================================================

IMPORTANT DATES (all deadlines 23:59 Anywhere on Earth)

Paper submission ............ 9 December 2026
Notification of acceptance .. 9 February 2027
Camera-ready version ........ 28 February 2027
Conference .................. 19-21 March 2027

Submission (EDAS): https://edas.info/newPaper.php?c=35773

-----------------------------------------------------------------------
SCOPE
-----------------------------------------------------------------------

Since 2007, WISTP has brought together researchers and practitioners
working on the security of systems that operate under real
constraints: embedded devices, smart cards, networks and
cyber-physical infrastructure. The 2027 edition carries that focus
into the era of large language models and autonomous agents, whose
security and privacy implications now reach those same environments.

WISTP 2027 solicits original submissions from academia and industry
across the full range of theoretical and practical dimensions of
security and privacy, and gives particular prominence to the
cybersecurity of LLMs and agentic AI: systems that now hold
credentials, invoke tools, and act on the networks and embedded
infrastructure WISTP has studied since 2007.

Experimental studies of fielded systems, reports on deployments and
lessons learned, and contributions from the law, business and policy
communities are all explicitly welcome.

HYBRID BY DESIGN. Every session is streamed, and every accepted paper
may be presented remotely and live, in its own slot, with questions
and discussion. A documented visa refusal is never treated as a
no-show. Authors who cannot travel to Djerba are explicitly encouraged
to submit.

-----------------------------------------------------------------------
TOPICS OF INTEREST (indicative, not exhaustive - full list online)
-----------------------------------------------------------------------

* Cybersecurity of Large Language Models and Agentic AI
- Prompt injection (direct, indirect, multimodal), jailbreaking,
guardrail bypass and automated red-teaming
- Alignment robustness, fine-tuning degradation, sleeper backdoors
- System-prompt extraction, training-data memorisation and
membership inference; model stealing and watermarking
- Retrieval-augmented generation: knowledge-base poisoning, context
integrity and provenance
- Security of LLM-generated code, hallucinated dependencies,
model supply chain and unsafe serialisation
- Agent hijacking, goal manipulation, confused-deputy attacks,
tool and skill poisoning, persistent memory poisoning
- Security of agent interoperability protocols (MCP, agent-to-agent,
tool use); sandboxing and least privilege for code-executing and
computer-use agents
- Identity, delegation, authorisation and capability tokens for
non-human actors; multi-agent trust, collusion, cascading failure
- Human oversight and interruptibility; observability, audit trails
and forensics of agent actions; autonomous offence and defence
- Agentic supply chain (plugins, skills, marketplaces);
accountability, liability and assurance of agentic deployments

* Security and Privacy in Artificial Intelligence
- Adversarial machine learning: evasion, poisoning, backdoors
- Privacy-preserving ML: differential privacy, homomorphic
encryption, secure multi-party computation
- Federated learning security: gradient leakage, secure aggregation,
Byzantine-robust FL
- Model extraction, inversion and membership inference
- Generative-AI risks: deepfakes, synthetic identity
- AI governance, accountability, regulatory compliance,
AI supply-chain security

* Security and Privacy in Smart Devices
- Smart cards, TPMs, RFID, wireless sensor nodes, biometrics and
national ID cards
- Mobile OS and mobile code security, mobile malware
- On-device AI and edge inference: weight confidentiality,
attestation, TEEs for model, prompt and context confidentiality
- Side-channel and fault attacks on neural accelerators and NPUs
- Generative presentation attacks on biometric systems;
agentic assistants holding OS, accessibility or payment privileges

* Security and Privacy in Networks
- Ad hoc, sensor, body-area, vehicular, delay-tolerant, peer-to-peer
and content-centric networks; Bluetooth, NFC, WiFi, cellular
- AI-based network anomaly detection; security of AI-optimised
protocols; AI-native functions in 5G/6G and Open RAN
- Security of agent-to-agent communication and tool-invocation
protocols; side channels in encrypted LLM and agent traffic
- LLM-driven protocol analysis and fuzzing; agentic and intent-based
network management; abuse and DoS by autonomous crawlers and
agent swarms; federated training over constrained networks

* Security and Privacy in Architectures, Protocols, Policies,
Systems and Applications
- Cloud, distributed and cyber-physical systems, IoT, critical
infrastructure and industrial control, smart cities
- Identity and trust management, access control, authentication,
data protection, privacy-enhancing technologies, lightweight
cryptography, intrusion detection, security measurements
- Security policies and human behaviour; public administration and
governmental services; mobile commerce; social networks
- LLM and agentic systems in critical infrastructure; agentic
workflows in the cloud and blast-radius control; IAM for
non-human actors; security of AI-assisted development and CI/CD
- LLM-assisted threat intelligence, detection engineering and
digital forensics; automated social engineering at scale
- Regulatory compliance for AI and agentic systems; trust,
reputation and contract models for autonomous agents;
transactional and payment-capable agents

-----------------------------------------------------------------------
SUBMISSION
-----------------------------------------------------------------------

Paper categories (Springer LNCS format, LaTeX llncs class preferred):

Full paper ..................... 16 pages excl. references (25 min)
Short paper / work in progress .. 8 pages excl. references (12 min)
Systematization of Knowledge ... 16 pages (25 min)
Industry and practice .......... 8-16 pages (20 min)

Reviewing is DOUBLE-BLIND: submissions must not identify their
authors. Work must be unpublished and not under review elsewhere.
Papers involving human subjects, personal data or vulnerability
discovery must describe the ethical safeguards applied. Any use of
generative AI beyond language editing must be declared.

At least one author of each accepted paper must register at the full
rate by 28 February 2027 and present the paper, on site or remotely.

Submission guidelines: https://wistp2027.roc.cnam.fr/?page_id=12
Submit on EDAS: https://edas.info/newPaper.php?c=35773

-----------------------------------------------------------------------
ORGANISATION
-----------------------------------------------------------------------

WISTP 2027 is organised by the IReSCoMath Lab of the University of
Gabès (Tunisia) and the CEDRIC Lab of Conservatoire national des arts
et métiers (Paris, France).

General Chairs
Samia Bouzefrane, Cnam, France
Haifa Touati, University of Gabès, Tunisia

Program Chairs
Issam Jabri, University of Gabès, Tunisia
Sabrine Khriji, Chemnitz University of Technology, Germany

Honorary Chairs
Damien Sauveron, University of Limoges, France
Farouk Kamoun, ENSI, University of Manouba, Tunisia

Steering Committee
Angelos Bilas (FORTH-ICS & University of Crete), Olivier Blazy
(LIX, École Polytechnique), Konstantinos Markantonakis (Royal
Holloway, University of London), Joachim Posegga (University of
Passau), Jean-Jacques Quisquater (UCLouvain), Damien Sauveron
(University of Limoges), Chan Yeob Yeun (Khalifa University)

Publicity Chairs
Yulliwas Ameur, Cnam, France
Eya Ben Charrada, University of Gabès, Tunisia

Full committees: https://wistp2027.roc.cnam.fr/?page_id=371

-----------------------------------------------------------------------
CONTACT
-----------------------------------------------------------------------

General enquiries: yulliwas.ameur@lecnam.net
Website: https://wistp2027.roc.cnam.fr
Hashtag: #WISTP2027

=======================================================================